Robotic systems and methods for assisting a user from standing to sitting

Abstract

Robotic systems and methods related to assisting a subject are disclosed. A robotic system may include a plurality of serially connected linkages which can be articulated to mirror a posture of the subject and / or transition the subject to a seated posture. The robotic system may comprise a plurality of actuators configured to move the plurality of serially connected linkages between a standing support configuration and a seated support configuration. The robotic system may include one or more moveable robotic limbs extending from one or more of the plurality of serially connected linkages that may be configured to be engaged with a body of the subject to facilitate transitioning the subject from the standing configuration to the seated configuration.

Description

MIT 25833- 1 -ROBOTIC SYSTEMS AND METHODS FOR ASSISTING A USER FROM STANDING TO SITTINGRELATED APPLICATIONS

[0001] This Application claims the benefit of priority under 35 U.S.C. § 119(e) of U.S. Provisional Application Serial No. 63 / 709,382, filed October 18, 2024, the disclosure of which is incorporated herein by reference in its entirety.FIELD

[0002] Disclosed embodiments are related to robotic systems and methods for assisting with user posture.BACKGROUND

[0003] Falls in the elderly population or in populations with health conditions are a major public health issue. Serious injuries may result from a fall that may lead to rapidly declining health. There have been some mobile robot solutions to aid balance while walking to prevent falls. These systems typically include a mobile platform that moves with the user with an upper frame that connects to the user via short tethers connected to a wearable harness. With these systems, the user must always be tethered to the device to prevent a potential fall. Other solutions require a U-shaped fork to surround a person at all times. Air bags may be attached to this fork that inflate when a fall is detected. These systems generally encumber a user and inhibit physical movement.SUMMARY

[0004] In some embodiments, a robotic system configured to assist a subject may comprise a plurality of serially connected linkages, a plurality of actuators configured to move the plurality of serially connected linkages between a standing support configuration and a seated support configuration, and one or more moveable robotic limbs extending from one or more of the plurality of serially connected linkages. In some embodiments, the one or more moveable robotic limbs may be configured to be engaged with a body of the subject.#14424435vl

[0005] In some embodiments, a method of assisting a subject with a robotic system may comprise monitoring a posture of the subject, predicting a need for assistance based on the posture of the subject, engaging the subject with one or more robotic limbs of the robotic system connected to a plurality of serially connected linkages, and transitioning the plurality of serially connected linkages from a standing support configuration to a seated support configuration.

[0006] In one embodiment, the disclosed system further comprises a sensory system configured to (continuously, periodically) track a location of the subject.

[0007] In one embodiment, the disclosed system further comprises a computer comprising a processor, wherein the sensory system is an input into the computer.

[0008] In one embodiment, the disclosed system further comprises a power supply, wherein the power supply enables the computer to control the joints, hinges, and wheels.

[0009] In one embodiment of the disclosed system, the exoskeleton actively tracks and mimics the subject’s posture.

[0010] In one embodiment of the disclosed system, the base continually moves to situate itself behind the subject and provide support as needed.

[0011] In one embodiment of the disclosed system, the base optionally comprises a pair of wheels that extend to provide additional stability and support as needed.

[0012] In one embodiment of the disclosed system, each of the arms further comprises a brace mounted on the vertical exoskeleton, wherein the brace is configured to provide mechanical strength to the arm.

[0013] In one embodiment of the disclosed system, the arms are configured to bear a vertical load created by the subject.

[0014] In one embodiment of the disclosed system, in the event of a fall, the robotic arms are located closely behind the subject and are configured to quickly and gently grasp the subject to prevent the fall.

[0015] In one embodiment of the disclosed system, the vertical exoskeleton folds into a chair and is connected to the vertical support of the compact mobile base.

[0016] In one embodiment of the disclosed system, the vertical exoskeleton is configured to continually guide the subject through a predetermined safe stand-to-sit trajectory based under control by the computer.#14424435vl

[0017] In one embodiment of the disclosed system, the vertical exoskeleton further comprises a scissor linkage with an extension spring to guide and slow descent of the subject to a sitting position.

[0018] One aspect of the disclosure is a method of supporting a subject using the disclosed system.

[0019] One aspect of the disclosure is a clinic for physical therapy comprising the disclosed system.

[0020] One aspect of the disclosure is a computer system for controlling the disclosed support system, the computer system comprising: a processing system, computer storage accessible to the processing system, and computer program instructions encoded on the computer storage, wherein when the computer program instructions are processed by the processing system, the computer system is configured to define data structures in the computer storage representing the position and location of the subject, and execute a computer program applied to the data structures to assist (provide mechanical support to) the subject.

[0021] In one embodiment, the disclosed computer system further comprises a means of tracking sensory signals from the sensory system of the support system and to (continuously, periodically) track a location of the subject.

[0022] In one embodiment of the disclosed computer system, the computer program was generated by machine learning.

[0023] One aspect of the disclosure herein is a computer program product comprising computer storage and computer program instructions encoded on the computer storage, wherein the computer program instructions, when processed by a processing system of a computer, causes the computer to perform the disclosed or implement the disclosed computer system.

[0024] It should be appreciated that the foregoing concepts, and additional concepts discussed below, may be arranged in any suitable combination, as the present disclosure is not limited in this respect. Further, other advantages and novel features of the present disclosure will become apparent from the following detailed description of various nonlimiting embodiments when considered in conjunction with the accompanying figures.

[0025] In cases where the present specification and a document incorporated by reference include conflicting and / or inconsistent disclosure, the present specification shall#14424435vlcontrol. If two or more documents incorporated by reference include conflicting and / or inconsistent disclosure with respect to each other, then the document having the later effective date shall control.BRIEF DESCRIPTION OF DRAWINGS

[0026] The accompanying drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component that is illustrated in various figures may be represented by a like numeral. For purposes of clarity, not every component may be labeled in every drawing. In the drawings:

[0027] FIG. 1A depicts a schematic representation of a robotic system 100 according to some embodiments;

[0028] FIG. IB depicts a schematic representation of the robotic system 100 comprising linear actuators according to some embodiments;

[0029] FIG. 2 A depicts a schematic representation of a robotic system 100 in an at least partially vertical orientation relative to a local direction of gravity when the system is disposed on level ground according to some embodiments;

[0030] FIG. 2B depicts a schematic representation of the robotic system 100 of FIG.2A transitioning from the standing configuration to a seated configuration according to some embodiments;

[0031] FIG. 2C depicts a schematic representation of the robotic system 100 of FIGs. 2A-2B in a seated configuration according to some embodiments;

[0032] FIG. 3 A depicts a schematic representation of a robotic system 100 in a standing configuration according to some embodiments;

[0033] FIG. 3B depicts a schematic representation of the robotic system 100 of FIG.3 A in a seated configuration according to some embodiments;

[0034] FIG. 4 A depicts a schematic representation of a robotic system 100 tracking a subject 200 according to some embodiments;

[0035] FIG. 4B depicts a schematic representation of the robotic system 100 of FIG.4A articulating away from the vertical orientation to assist the subject 200 according to some embodiments;

[0036] FIG. 4C depicts a schematic representation of the robotic system 100 of FIGs. 4A-4B assisting the subject 200 according to some embodiments;#14424435vl

[0037] FIG. 4D depicts a schematic representation of the robotic system 100 of FIGs. 4A-4C transitioning the subject 200 to a seated configuration;

[0038] FIG. 4E depicts a schematic representation of the robotic system 100 of FIGs.4A-4D transitioning the subject 200 to a seated configuration according to some embodiments;

[0039] FIG. 4F depicts a schematic representation of the robotic system 100 of FIGs.4A-4E supporting the subject 200 in the seated configuration according to some embodiments;

[0040] FIG. 5 A depicts a schematic representation of the robotic system 100 comprising linear actuators tracking the subject 200 according to some embodiments;

[0041] FIG. 5B depicts a schematic representation of the robotic system 100 of FIG.5 A articulating away from the vertical orientation according to some embodiments;

[0042] FIG. 5C depicts a schematic representation of the robotic system 100 of FIGs.5A-5B supporting the subject 200 in the seated configuration according to some embodiments;

[0043] FIG. 6 depicts a block diagram of a computer 500 configured to control a robotic system 100 according to some embodiments;

[0044] FIG. 7 depicts a method flow chart 600 of assisting a subject with a robotic system 100 according to some embodiments;

[0045] FIG. 8 depicts a flow chart 700 of behavior modes of a robotic system 100 according to some embodiments;

[0046] FIG. 9 depicts an extension range frommin tomax of one or more robotic limbs of the robotic system 100 with penalties for extensions outside the extension range according to some embodiments;

[0047] FIG. 10 depicts coordinate systems used for motion planning of the robotic system 100 according to some embodiments;

[0048] FIG. 11 depicts a low-level control architecture 1100 of a mobile base 112 of a robotic system 100 according to some embodiments;

[0049] FIG. 12 depicts a control architecture 1200 of a robotic system 100 according to some embodiments;

[0050] FIG. 13 A depicts a reference end effector position trajectory in a forward direction according to some embodiments;#14424435vl

[0051] FIG. 13B depicts a graphical representation of a distribution of degrees of freedom of motion of the robotic system 100 for different penalty values;

[0052] FIG. 13C depicts a graphical representation of a change in the distribution of the robotic system 100 degrees of freedom of motion from phase 1 to phase 2 with a particular penalty value;

[0053] FIG. 14A depicts simulated and real arm joint angle trajectories of the robotic system 100 according to some embodiments;

[0054] FIG. 14B depicts simulated and real arm convertible backbone joint angle trajectories of the robotic system 100 according to some embodiments; and

[0055] FIG. 14C depicts simulated and real mobile base 112 motion according to some embodiments.DETAILED DESCRIPTION

[0056] A fall by an elderly subject or other person may result in serious injury. In institutional settings, the standard for caregivers assisting an elderly person falling is to slowly lower them to the floor. Once on the floor, some institutions require going through certain procedures before attempting to lift the person up. This is to ensure that possible injuries from the fall are not aggravated during the lifting phase. Once on the floor, it may be difficult for the elderly subject to get back up again. In the home, an elderly spouse may not be able to help them, and oftentimes an ambulance is called to get them up from the floor.

[0057] Many prior systems for preventing falls in users (e.g., subjects), such as elderly users during various activities, may include a stationary or mobile base that moves with the user with an associated rigid upper frame that connects to the user via short tethers and a wearable harness. The Inventors have recognized that systems requiring attachment to a user such as a harness and rigid frame and / or wearing of safety structures such as vests and belts are undesirable from a practical perspective for certain activities and / or personal preferences for users. For example, systems requiring a rigid frame to constantly surround a user would encumber them and limit their physical mobility. The Inventors have appreciated that these limitations associated with the use of prior fall prevention systems may cause people to be less likely to adopt these systems as they are inconvenient to use and may restrict their ability to perform everyday tasks.#14424435vl

[0058] In view of the above, the Inventors have recognized the need for less restrictive fall prevention systems. Accordingly, the Inventors have recognized that a fall prevention aid that follows the subject from behind and offers support as needed would be less restricting and therefore may have a significantly higher likelihood of adoption by elderly subjects. In this regard, the Inventors have recognized the benefits associated with a robotic system that is configured to contactlessly monitor a subject and detect high-effort and / or unstable postures associated with falls or potential falls in real time. In some embodiments, the robotic system may follow a subject moving through an environment and contactlessly monitor the subject’s posture in order to perform close supervision of the subject. Accordingly, in some embodiments, a robotic system may be configured to monitor a subject’s posture and detect high-effort postures and / or posture transitions where assistance may be desired (e.g., postures associated with falls). The Inventors have recognized that a contactless monitoring system can be beneficial for overcoming the limitations of prior monitoring systems discussed above.

[0059] Some prior systems prevent fall injuries from hard ground contact, such as wearable hip and vest airbags and / or harnesses that slowly lower the user to the ground. While these devices may prevent injury from ground contact, there is still the issue of getting up from the floor. In view of this difficulty, the Inventors have appreciated the advantages of transitioning a subject to a seated position. For example, the Inventors have recognized that it can be more convenient and / or require less assistance for a subject to return to a standing posture from a seated posture as opposed to standing up once on the floor or ground. The Inventors have therefore recognized that putting the person in a sitting position, or position they can easily stand up from unassisted, can be advantageous to letting them fall to the floor, even in a controlled manner. Therefore, the Inventors have appreciated the benefits associated with transitioning a subject to a seated position when they are falling and / or may be in an unstable and / or high effort posture.

[0060] In some embodiments, a robot can support the subject throughout a variety of postures, catch a person falling, and / or pull them into a sitting position. In some embodiments, the robotic system may comprise a mobile base and a backbone. The backbone may include a plurality of serially connected linkages. In some embodiments, such a backbone may comprise multiple links that are normally colinear but can be articulated between a standing configuration and a seated configuration. For example, the backbone may be configured to fold from an at least partially vertical or standing configuration into a seated#14424435vlconfiguration where at least a portion of the backbone may function as a chair. Also, as discussed further below, in some embodiments the robotic system may comprise one or more robotic limbs that can grasp a person and safely bring them toward the robot.

[0061] In view of the above, the Inventors have recognized that a benefit of an actuated backbone situated behind the subject is that the actuated backbone may mimic the subject’s upper body and / or position attached robotic arms close to the subject’s torso. In some embodiments, the robotic system may comprise one or more robotic limbs which are maintained within reach of the person. In some embodiments, the robotic system may maintain the robotic arms away from the subject and deploy the robotic arms close to the subject’s torso. For example, in some embodiments, the robotic system may comprise lightweight arms with inflatable coverings or other appropriate arrangement that can grasp the subject and bring them toward the robot. Accordingly, the robotic limbs can wrap around the subject’s torso and support them and / or transition them to a seated position when the robotic system detects a posture and / or other parameter associated with instability and / or a fall. Therefore, the robotic system may monitor the subject and engage the subject and then transition the subject to a seated position when the predicted stability level for a subject related to a determined posture indicates a fall is occurring or may be likely to occur. The Inventors have appreciated that such a robotic system may be beneficial for improved monitoring and / or assistance of the subject compared to the previous system described above. For example, the user may be able to stand up from the seated position with less effort than prior systems which required the user to stand up from the floor.

[0062] The Inventors have recognized that a system that can provide contactless fall assistance and / or transition a user to a seated position based on a detected posture or instability may be beneficial for reducing instances of falls in real time and / or improving overall care provided to users. In some embodiments, a robotic system may obtain pose information of a user with one or more sensors configured to sense pose information of the user proximate to a base or other portion (e.g., linkage) of the system. The robotic system may then determine a posture and / or a posture transition of the user based at least in part on the sensed pose information. Depending on the posture and / or a posture transition of the user that is detected by the robotic system, the robotic system may determine that it is desirable to transition the user to a seated position as discussed previously above. In some embodiments, the robotic system is operated based on a determined posture and / or posture transition of the#14424435vluser. Upon determining that assistive forces are desired, the robotic system may control one or more robotic limbs of the robotic system to engage with a user to apply the desired assistive force to the user’s body and transition the user to a seated position. From the seated position, the subject can stand back up on their feet and return to moving in the overall environment.

[0063] In some embodiments, a robotic system may be configured to assist a person in any appropriate posture and / or posture transition where the user may be unstable and / or at risk of falling. Upon determining a user may be unstable and / or falling, the robotic system may be operated such that the one or more robotic limbs secure the user relative to the backbone. Once engaged with the user, the robotic system may be operated such that the user is transitioned from a standing posture to a seated posture. Accordingly, in some embodiments, the robotic system may comprise a plurality of serially connected linkages and a plurality of actuators configured to move the plurality of serially connected linkages between a standing support configuration and a seated support configuration. The robotic system may further comprise one or more moveable robotic limbs extending from one or more of the plurality of serially connected linkages. As such, the robotic system can monitor a subject and the one or more actuators can move the plurality of serially connected linkages and / or the one or more moveable robotic limbs to engage with the body of the subject (e.g., when a fall and / or unstable posture is detected). For example, the one or more actuators can transition the plurality of serially connected linkages from the standing support configuration to the seated support configuration.

[0064] It should be understood that any appropriate type of rigid and / or flexible type of robotic limb capable of being operated to engage a user’s body may be used in the various embodiments disclosed herein as the disclosure is not so limited. In some embodiments, the robotic system may comprise chain-like limbs comprising a plurality of relatively small linkages connected together which may be controlled to bend by cables. In some embodiments, the robotic system may comprise one or more inflatable robotic limbs that wrap around the subject as they deploy. In some embodiments, the robotic system may comprise one or more rigid robotic limbs configured to engage the subject. In some embodiments, the one or more robotic limbs may comprise an end effector configured to contact the subject. In some embodiments, the end effector may be cushioned. Additionally or alternatively, the end effectors may comprise force sensors to measure a contact force#14424435vlbetween the end effector and the subject which may be beneficial for controlling the movement of the one or more robotic limbs.

[0065] Depending on the embodiment, the robotic systems disclosed herein may either be mobile or stationary robotic systems. For example, in some embodiments, a robotic system may include one or more mobile bases configured to support one or more robotic limbs operatively connected thereto to assist a user while the user moves freely within an overall environment. Accordingly, the robotic system having a mobile base can be beneficial for tracking the subject through the overall environment without inhibiting or restricting the subject’s movements. It is appreciated that a mobile base may comprise any desired configuration depending on the embodiment as the disclosure is not so limited. Accordingly, in some embodiments, the mobile base may comprise a swerve drive. For example, one or more wheels may be mounted to the mobile base and may be independently controllable for omnidirectional movement as will be appreciated by those of skills. In some embodiments, the mobile base may comprise a track drive. In this regard, one or more tracks may be mounted to the mobile base and may be independently controllable to move the robotic system in an overall environment. Of course, mobile bases comprising other types of movement system are contemplated as the disclosure is not so limited.

[0066] In some embodiments, the various types of pose information sensed for a user may be evaluated using thresholding relative to a threshold parameter to determine if a user is in a particular posture, posture transition, and / or falling. In some embodiments, if one or more parameters exceed a threshold, then the robotic system may detect a fall and assist the user (e.g., by transitioning the user to the seated position, etc.) For example, in one embodiment, one or more sensors may detect the position, velocity, and / or acceleration of the center of mass of the person. According to this embodiment, a fall catching operation system may be activated when the position, velocity, and / or acceleration of the center of mass of the person exceeds a certain threshold vertical position, velocity, and / or acceleration indicative of a fall and / or instability. Additionally or alternatively, thresholding in a vertical and / or lateral direction relative to a threshold velocity and / or displacement of the center of mass may be used to determine postures and / or posture transitions associated with falling and / or unstable movement. In some embodiments, a fall may be predicted by detecting the user’s center of pressure, or zero moment point, to determine if such a point moves outside the user’s support polygon. Of course, any desired parameter and / or threshold may be used to detect posture,#14424435vlposture transitions, instability in a subject’s posture, and / or falling as the disclosure is not so limited.

[0067] In some embodiments, a trained artificial intelligence model can predict the need for assistance of the user. In some embodiments, the robotic system may use any of the previously mentioned pose information of a user in combination with a trained statistical and / or artificial intelligence model to determine a posture and / or posture transition that the user is undergoing. For example, pose information may be input into the trained statistical model which may output a determined posture and / or posture transition of the user to predict a need for assistance such as the user is falling or is likely to fall. The trained statistical model may be trained using ground truth data corresponding to any of the types of postures and posture transitions noted above in combination with the pose information sensed by the one or more sensors of the robotic system. Appropriate types of trained statistical models may include but are not limited to Bayesian inference or Bayesian networks. Appropriate training methods may also include but are not limited to neural networks with gradient descent or using machine learning where a model is trained with gradient descent on data from any of the aforementioned sensing modalities (cameras, inertial measurement units, foot sole sensors, radar, Wi-Fi signals, etc.). In this manner, a trained statistical model can be used to predict a need for assistance. For example, a trained statistical model can be used to detect a fall or other unstable posture in order to provide assistance to the subject.

[0068] While particular methods for determining a posture and / or posture transition of a user are discussed above, it should be understood that any method may be used to determine a posture and / or posture transition of a user as the disclosure is not so limited.

[0069] As noted above, the Inventors have recognized the benefits associated with a robotic system that can actively sense a posture and / or posture transition of a user based at least in part using detected pose information. This may help to provide a robotic system that can contactlessly monitor a user and / or transition the user to a seated posture upon detecting a fall and / or unstable posture. To provide the desired pose information, in some embodiments, a robotic system may include one or more sensors configured to sense pose information of the subject. For example, in some embodiments one or more parameters related to a pose of a user (i.e., pose information) can be sensed. The one or more sensors may be configured to transmit one or more corresponding signals with the desired pose information to one or more associated processors in an associated local or remote controller to facilitate control of the#14424435vlplurality of actuators, the one or more robotic limbs, the plurality of serially connected linkages, and / or the mobile base. The one or more processors may be configured to determine the posture and / or a posture transition of the subject based at least in part on the sensed pose information. The one or more processors may also be configured to control the one or more moveable robotic limbs to be engaged with the subject’s body based at least in part on the determined posture and / or posture transition of the subject while the plurality of serially connected linkages are in the standing support configuration. Accordingly, the robotic system can assist a subject in transitioning from a standing posture to a seated posture. Accordingly, in some embodiments the one or more processors may be configured to control the plurality of actuators to transition the plurality of serially connected linkages from the standing support configuration to the seated support configuration.

[0070] It should be understood that any appropriate type of sensor may be used to sense the desired pose information related to a user’s body. In some embodiments the one or more sensors may include a 3-D vision system configured to collect 3D information about the pose of one or more portions of the user’s body. According to this embodiment, the vision system may track the position of a person’s joints and / or certain nodes on the user’s body to collect pose information. The vision system may also monitor certain angular orientations of the person’s joints and / or nodes to collect information about the changes in pose. In some embodiments, the one or more sensors may include position sensors, joint angle sensors, inertial measurement units, accelerometers, position encoders, potentiometers, displacement sensors, angular sensors, torque sensors, cameras, force sensors in a wearable article of a user (e.g., shoes) of a user, combinations of any of the above forgoing sensors, and / or any other appropriate sensors configured to sense information related to a posture and / or a transition between postures of the user’s body. Depending on the type of sensor, the one or more sensors may either detect the desired pose information through direct and / or indirect sensing of the pose information of the user’s body.

[0071] A pose and / or overall configuration of the robotic system may be determined using any appropriate method. For example, a configuration of a robotic system, including the one or more robotic limbs during operation, may be determined by using forward and / or inverse kinematics in combination with the associated robotic limb position and / or force sensors. Forward kinematics may use kinematic equations to determine the pose of the robotic system using known values for joint parameters (e.g., sensed angles of the joint,#14424435vlmeasured by potentiometers). Inverse kinematics may use kinematic equations to determine the joint parameters needed to achieve a corresponding assistance system pose. Alternatively, a pose of the robotic system may be determined using one or more sensors, such as one or more sensors and corresponding pose tracking algorithms which may be used to identify the robotic system within the image and determine a pose of the robotic system within the three- dimensional space observed by the one or more photosensitive detectors. The pose of the robotic system may include, but is not limited to, the pose of the one or more robotic limbs, the first and / or second mobile bases, the relative pose of the first and second mobile bases, and / or any other appropriate portion of the robotic system.

[0072] As used herein, a pose may refer to an orientation and position of a component, user, device, user, or other object. In some embodiments, the pose may be a position in three-dimensional space in combination with a particular angular orientation within three-dimensional space. For example, a relative pose of a device relative to a user may refer to the position and angular orientation of the device relative to the user. In reference to a person, a pose may entail the body position and / or orientation of one or more portions of a user’s body. Further, a posture may refer to a combination of poses of the various portions of a user’s body associated with the various poses noted above (e.g., sitting, standing, reaching, kneeling, etc.).

[0073] It should be appreciated that the robotic systems described herein may be employed for any number of different suitable uses in a number of different environments. In one example, the disclosed robotic systems may be employed in a home of a user with limited strength and / or mobility (e.g., an elderly user or a physically disabled user), a hospital for temporary or permanently low-strength users, an assisted living community, a physical rehabilitation facility, and / or any other suitable environment to where it may be desirable to assist with a user performing activities within an environment while assisting in maintaining a user’s stability, aiding the user during posture transitions, and / or for preventing and / or mitigating falls of the user. Thus, it should be understood that the disclosed robotic systems are not limited to any specific environment and / or application.

[0074] Turning to the figures, specific non-limiting embodiments are described in further detail. It should be understood that the various systems, components, features, and methods described relative to these embodiments may be used either individually and / or in#14424435vlany desired combination as the disclosure is not limited to only the specific embodiments described herein.

[0075] Figure 1A depicts a schematic representation of a robotic system 100 according to some embodiments. The robotic system 100 can be configured to assist a subject (e.g., by providing contact assistance and / or guiding the subject to a seated position). In the depicted embodiment, the robotic system 100 comprises a plurality of serially connected linkages 102. In the depicted embodiment, a first linkage of the plurality of serially connected linkages comprises a seat 102a configured to support the subject in the seated support configuration. Further, a second linkage of the plurality of serially connected linkages 102 comprises a seatback 102b configured to further support the subject in the seated support configuration. In some embodiments, the plurality of serially connected linkages 102 may comprise one or more joints between each linkage 102a, 102b, which may be beneficial for articulating the plurality of linkages 102 (e.g., to align with the subject’s posture and / or transition to a seated position). In the depicted embodiment, the robotic system 100 comprises a knee joint 120a between the seat 102a and the mobile base 112. The robotic system 100 also comprises a hip joint 120b between the seat 102a and the seatback 102b. Accordingly, it is appreciated that the plurality of linkages 102 may be configured to articulate in order to mirror the posture of the subject and / or transform between a standing position and a seated position.

[0076] In some embodiments, the plurality of serially connected linkages 102 can be dimensioned to correspond with the subject’s anatomy. Accordingly, in some embodiments a length of each of the links of the plurality of serially connected linkages 102 can be configured to match a height range of a subject and / or be aligned with a hip and / or knee joint (e.g., knee joint 120a may align with the subject’s knee joint and / or the hip joint 120b may align with the subject’s hip joint) during at least one mode of operation. In this regard, in some embodiments, the robotic system 100 may have one or more joints aligning with a subject’s hip and / or knee and / or other joint. This can be beneficial for supporting the subject and / or transitioning the subject to a seated posture as described above. Accordingly, it is appreciated that the robotic system 100 may comprise links that align with the subject’s anatomy in order to support the subject between and / or in a standing position and a seated position.#14424435vl

[0077] In some embodiments, one or more links of the plurality of linkages 102 may have a length and / or width greater than or equal to 20 cm, 30 cm, 40 cm, 50 cm, 60 cm, or other desired length and / or width. In some embodiments, the one or more links of the plurality of linkages may have a length and / or width less than or equal to 100 cm, 90 cm, 80 cm, 70 cm, 60 cm, 50 cm, or other desired length and / or width. Combinations of the above ranges are also contemplated as the disclosure is not so limited. For example, in some embodiments, the one or more links of the plurality of linkages may comprise a length and / or width between or equal to 20 cm and 100 cm.

[0078] In some embodiments the robotic system 100 may comprise one or more moveable robotic limbs 104 extending from one or more of the plurality of serially connected linkages 102. For example, in the depicted embodiment, the robotic system 100 comprises a left arm 104a and a right arm 104b which each extend from the seatback 102b. In the depicted embodiment, the left and right arms 104a, 104b can be articulated using a shoulder joint 126 and an elbow joint 128. Accordingly, the left arm and the right arm 104a, 104b can be configured to move and engage a subject in order to stabilize the subject and / or guide the subject between a standing position and a seated position as described herein when the associated backbone including the plurality of serially connected linkages 102 is articulated between the standing and seated configurations. In this regard, the one or more moveable robotic limbs 104 may be configured to be engaged with a body of the subject. In some embodiments, the one or more robotic limbs 104 may comprise an end effector 114 configured to contact the subject’s body when engaged with the subject. It is appreciated that in some embodiments, the end effector may comprise a cushioned end effector configured to contact the subject which may be beneficial for comfort and / or safety. Of course, it is appreciated that in some embodiments, the one or more robotic limbs 104 may comprise a rigid end effector as the disclosure is not so limited. In some embodiments, the one or more robotic limbs 104 and / or the end effectors 114 may comprise a force sensor to sense contact with the subject. The force sensor may be beneficial for controlling movement of the one or more robotic limbs 104 by detecting when the one or more robotic limbs 104 are in contact with the subject and / or how much force is being applied by the one or more robotic limbs 104 to the subject.

[0079] As mentioned above, the robotic system 100 may be configured to articulate in order to contact a subject and / or transform between a standing position and a seated position.#14424435vlIn order to move the plurality of linkages 102 and / or the one or more robotic limbs 104, the robotic system may comprise actuators in some embodiments. In this regard, the robotic system 100 may comprise a plurality of actuators 106 configured to move one or more parts of the robotic system 100 (e.g., the one or more robotic limbs 104 and / or one or more of the plurality of linkages 102). For example, in some embodiments, the one or more actuators 106 may be configured to articulate the plurality of serially connected linkages 102 between a standing support configuration and a seated support configuration as discussed further below.

[0080] It is appreciated that the actuators 106 are schematically depicted in FIG. 1. In other words, while the actuators 106 are depicted as connecting each of the plurality of linkages 102 to each other, to the mobile base 112, and to the left and right arms 104a, 104b, it is appreciated that the actuators 106 may be arranged in any desired manner in order control movement of the plurality of linkages 102 and / or the one or more robotic limbs 104. Further, the actuators 106 may comprise any type or combination of types of actuators such as electric actuators, pneumatic actuators, hydraulic actuators, linear actuators, electric motors, solenoids, or any other desired actuator as will be appreciated by those of skill as the disclosure is not so limited.

[0081] In some embodiments, the robotic system 100 may comprise a mobile base 112 and the plurality of serially connected linkages 102 may connect to the mobile base 112. In the depicted embodiment, the robotic system 100 comprises wheels 116 mounted to the mobile base 112. In this regard, the robotic system 100 may be configured to track the subject through the environment. As mentioned above, such a configuration may be beneficial for contactless supervision of the subject. Accordingly, the mobile base 112 may be configured to maintain a predetermined pose relative to the subject (e.g., maintain a desired distance and / or position relative to the subject, etc.). In some embodiments, achieving a desired pose or position of the robotic system 100 may comprises moving the mobile base 112, moving the one or more robotic limbs 104, and / or moving the plurality of serially connected linkages 102. It is appreciated that the mobile base 112, the one or more robotic limbs 104, and / or the plurality of serially connected linkages 102 can be moved together or separately in any combination as the disclosure is not so limited. Accordingly, in some embodiments the robotic system 100 can control each of these systems in a coordinated manner to provide assistance to the subject. As described in more detail below, in some embodiments the robotic#14424435vlsystem 100 may follow a predetermined motion plan to contact the subject and / or transition the subject between a standing configuration and a seated configuration.

[0082] As mentioned above, the robotic system 100 may be configured to detect a posture and / or posture transition of the subject. Accordingly, in some embodiments, the robotic system 100 may comprise one or more sensors 108 configured to sense pose information of the subject. In the embodiment of FIG. 1 A, the robotic system 100 comprises the one or more sensors that are mounted to the seatback 102b. a sensor 108. It is appreciated that the robotic system 100 may comprise more than one type of sensor such as acceleration, position, velocity, etc. as the disclosure is not so limited. Additionally or alternatively, while the sensor 108 is mounted to the seatback 102b, it is appreciated that the sensor may be mounted anywhere on the robotic system as the disclosure is not so limited (e.g., on the mobile base, the seat 102a, etc.) and / or the subject may wear one or more sensors to detect posture information and / or a fall. In some embodiments, the robotic system 100 may comprise one or more sensors mounted to one or more locations as the disclosure is not so limited.

[0083] In some embodiments, the sensed posed information detected by the one or more sensors 108 may comprise a position, a velocity, and / or an acceleration of a center of mass of the subject; ground reaction force between feet of the subject and the ground; and / or a whole body angular momentum, or centroidal momentum, of the subject. In this regard, in some embodiments the one or more sensors may comprise one or more of a camera, an inertial measurement unit, an accelerometer, and / or a distance sensor. Of course, other sensors are also contemplated as the disclosure is not so limited. It is appreciated that the distance sensor may comprise any desired type of distance sensor as will be appreciated by those of skill. Accordingly, in some embodiments, the distance sensor may comprise lidar, radar, Wi-Fi, an ultrasonic sensor, or other sensor configured to detect and / or measure a distance.

[0084] In some embodiments, the robotic system 100 may determine a posture of the subject and whether to provide assistance based on the sensed pose information. In this regard, in some embodiments, the robotic system 100 may comprise one or more processors 110. In the embodiment of FIG. 1, the processor 110 is depicted as mounted to the mobile base 112, however it is appreciated that the processor 110 can be installed at any location on or in the robotic system. In some embodiments, the processor 110 may be remote from the#14424435vlrobotic system 100. In some embodiments, the processor may be configured to determine a posture and / or a posture transition of the subject based at least in part on the sensed pose information. Accordingly, the processor 110 may be capable of determining if intervention is needed based on the sensed pose information. In some embodiments, the processor 110 may control the one or more moveable robotic limbs 104 to be engaged with the subject’s body based at least in part on the determined posture and / or posture transition of the subject while the plurality of serially connected linkages 102 are in the standing support configuration. In some embodiments, the one or more processors 110 can be configured to control the mobile base 112 and the plurality of actuators 106 to maintain a pose of the plurality of serially connected linkages 102 relative to the body of the subject. Accordingly, the robotic system 100 can respond to movement of the subject and be prepared to provide assistance as desired. When the processor controls the robotic system 100, the processor 110 may minimize a cost function. For example, the processor 110 can use the cost function to reward desired positions of the robotic system 100 and / or the one or more robotic limbs. The cost function can also penalize not reaching a desired position, moving the mobile base 112 unnecessarily, or energy intensive movement. Accordingly, the processor 110 can use the cost function to control the mobile base 112 and / or the plurality of actuators 106 in a desirable and / or efficient manner. Further description of the cost function and penalties is discussed in the example below.

[0085] In some embodiments, the processor 110 may be configured to control the plurality of actuators 106 to transition the plurality of serially connected linkages 102 from the standing support configuration to the seated support configuration. In this regard, the processor 110 may coordinate movement of the robot and / or command desired positions of the one or more robotic limbs 104 and / or end effectors 114 relative to the subject.

[0086] FIG. IB depicts a schematic representation of the robotic system 100 comprising at least one linear actuator 107 according to some embodiments. The embodiment of FIG. IB comprises a similar constructions to that of FIG. 1A, however, one or more linear actuators 107 (one linear actuator 107 depicted in FIG. IB) can be connected between the base 112 and the seat 102a and / or the seat back 102b. Accordingly, the one or more linear actuators 107 can actuate the seat 102a and / or the seat back 102b between the standing and sitting configurations. In this regard, actuators 106 may not be located at the knee and / or hip joint 120a, 120b according to some embodiments. It is appreciated that the one or more linear#14424435vlactuators 107 can provide improved mechanical advantage for supporting the user and / or actuating the seat 102a and / or the seat back 102b.

[0087] Figures 2A-2C show the robotic system 100 in different positions according to some embodiments. As seen in FIGs. 2A - 2C, the robotic system 100 can translate from a standing configuration (FIG. 2A) to a seated configuration (FIG. 2C).FIG. 2A shows the robotic system 100 in a standing configuration while following the subject (follower mode) according to some embodiments. In FIG. 2A, the arms 104 are folded behind the plurality of serially connected links 102 (e.g., vertical exoskeleton) which may be beneficial for freedom of the subject to move uninhibited in their environment. Of course, in some embodiments, the one or more robotic limbs 104 may be extended while in follower mode as seen in FIG. 1 which the subject may grasp for support and / or deployed to provide support and / or grasp the subject. FIG. 2B depicts the robotic system 100 transitioning between the standing configuration of FIG. 2A and the seated configuration of FIG. 2C. Accordingly, in some embodiments the joints (120a, 120b, and / or other joints) may articulate to transition between different configurations. In some embodiments, the robotic system 100 may have a catching mode where the arms 104 wrap around the person and support the subject against a light weight padded frame. For example, in some embodiments, the processor 110 can actuate the arms 104 to wrap around the subject. As mentioned above, it is appreciated that in some embodiments, the arms 104 may be light weight and rigid. In some embodiments, the arms can contain an inflatable cuff or foam covering for the comfort and / or safety of the subject. In the depicted embodiment, the base (e.g., mobile base 112) may be compact and comprise active caster wheels or swerve drive wheels, whose wheel speeds and orientation can both be controlled allowing for near holonomic motion, however as discussed above, in some embodiments the mobile base 112 may comprise tracks or other structure to permit mobility. FIG. 2C depicts the robotic system 100 in a seated configuration. In this regard, the plurality of serially connected links 102 (e.g., the exoskeleton support) can collapse to a sitting position to support the seated subject.

[0088] Figures 3A-3B depict a schematic representation of the robotic system 100 according to some embodiments. In some embodiments, the plurality of serially connected linkages 102 (e.g., the exoskeleton) may comprise an extension spring 122 in some embodiments that functions to slow descent from a vertical position (FIG. 3 A) to a seated position (FIG. 3B) of the subject. In some embodiments, the robotic system may comprise a#14424435vlscissor linkage 124 which can guide the descent of the subject. Such a configuration may be beneficial for a more controlled movement and / or descent of the subject.

[0089] Figures 4A-4F depict the robotic system 100 assisting a subject 200 in a standing position as well as transitioning the subject 200 from the standing position to a seated position. Accordingly, FIGs. 4A-4F show the function of the disclosed robotic system 100 for mechanical support of the subject 200 according to some embodiments. As seen in FIG. 4 A, the robotic system 100 can monitor the subject 200 in a standing position. In some embodiments, the arms 204 may be connected to the seatback 102b (or other vertical panels) by a motorized joint and may comprise a support brace (not shown) that bears the vertical load associated with the subject.

[0090] In the depicted embodiment, the knee joint 120a of the robotic system 100 aligns with a knee joint 220a of the subject. Similarly, the hip joint of the robotic system 100 aligns with a hip joint 220b of the subject. As mentioned above, such anatomical alignment may be beneficial for supporting the subject 200 and / or transitioning the subject 200 between the standing configuration and the seated configuration. In the depicted embodiment, the robotic system 100 nominally acts as a following robot and provides mechanical aid. As seen in FIGs. 4B-4C, the robotic system 100 may control the one or more serially connected links 102 together or independently and / or the mobile base 112 in order to mirror a posture of the subject 200. This may be beneficial for grasping the subject 200 and / or being positioned to grasp the subject 200. The robotic system 100 can grasp the subject 200 and may thereby reduce a likelihood of a fall.

[0091] As seen in FIGs. 4D-4F, in some embodiments, the robotic system 100 can move the subject 200 to a seated position. In some embodiments, the robotic system may monitor the posture of the subject (e.g., with one or more sensors 108) or other parameters such as position, acceleration, and / or velocity of the center of mass of the subject to detect a fall and / or unstable posture. The robotic system 100 can assist the subject 200 by transitioning them to a seated position based on the detected posture or other parameter. In some embodiments, the robotic system 100 can predict a need for assistance when a detected parameter exceeds a threshold associated with a fall. For example, in some embodiments predicting a need for assistance comprises identifying when a velocity of a center of mass of the subject 200 exceeds a threshold velocity associated with a fall. Regardless of the metric#14424435vlused, when a fall or likely fall is detected, the robotic system 100 can provide assistance to the subject using any of the methods described herein.

[0092] In some embodiments, the subject 200 may wear one or more sensors which collect pose information. For example, the subject 200 may wear sensors in their shoes to collect and send information to the robotic system 100 about the pressure distributions in the sole of the shoe to gain pose information. In some embodiments, a ground reaction force between the subject’s feet and the ground can be sensed to determine a posture, posture transition, falling, and / or instability. In some embodiments, a robotic system may sense a whole body angular momentum of the subject to detect a fall and / or instability. In some embodiments, transitioning postures may include, but are not limited to, deviating from a vertical orientation to a non-vertical orientation, transitioning from a stable posture to an unstable posture, or other appropriate transition. In some embodiments, different postures may be determined using multiple thresholds relative to the sensed pose information to distinguish between different related postures and / or posture transitions. For example, a risk of falling may be determined by a series of thresholds where a value of a pose information parameter that is greater than a first threshold may be associated with a first posture and / or posture transition and a value of a pose information related to the sensed pose information parameter greater than a second threshold greater than the first threshold may be indicative of a second posture and / or posture transition (e.g., falling). In some embodiments, a fall may be detected via abnormal movement of the sensed joints and / or nodes (e.g., the knee joints 220a, hip joints 220b, etc.) of the subject 200. For example, if the knee joints 220a of the subject 200 reach a threshold acceleration in a non-forward direction, the robotic system 100 may detect a fall or transition posture. Additionally, threshold orientations may be used to determine orientation of one or more portions of the subject’s body relative to each other and / or gravity that may be indicative of a fall or other posture and / or posture transition (e.g., torso tilt angle, etc.). The robotic system 100 can therefore assist the subject 200 when a fall or unstable posture is detected.

[0093] In some embodiments, the robotic system 100 may follow a predetermined stand-to sit trajectory to transition the subject to the seated position when a fall is detected. In some embodiments, the predetermined stand-to sit trajectory may be generated by recording a person’s hip and knee angles while sitting, to achieve a natural motion. In this regard, the predetermined stand-to-sit trajectory can be tailored to the subject 200.#14424435vl

[0094] As mentioned above, in some embodiments the robotic system 100 comprises joints that can rotate which may comprise hinges . In some embodiments, the robotic system 100 may maintain a fixed pose behind the subject 200 while following the subject around. In some embodiments, the robotic system 100 may maintain a robotic back structure in an at least partially vertical orientation relative to a local direction of gravity when the system is disposed on level ground and when following the subject as seen in FIG. 4A and may articulate the robotic back structure away from the vertical orientation to align the robotic back structure with the subject’s posture (e.g., during a fall) as seen in FIG 4B. For example, the robotic system may maintain a fixed angle between a back 202b of the subject 200 and the seatback 102b when following the subject. In some embodiments, the robotic system 100 may maintain the fixed angle when transitioning from a standing position to a seated position. For example, as seen in FIGs. 4B-4C, the robotic system 100 may articulate the one or more robotic links 102 to maintain the fixed angle (e.g., parallel lines) between the body of the subject 200 and the one or more serially connected links 102. For example, in FIGs. 4A-4F, the robotic system maintains the angle between an upper torso 202b of the subject 200 and the seatback 102b.

[0095] It is appreciated that the robotic system 100 may be configured to receive a command from the subject 200 in some embodiments. For example, in some embodiments the robotic system 100 may comprise two transient modes which include engage mode, when the robotic system 100 moves to make contact with the subject 200 with the arms and / or one or more portions of the serially connected linkages, and release mode, when the robotic system 100 releases the subject 200 and returns to close supervision mode. In engage mode, the robotic system 100 may wrap its robotic limbs 104 around the subject. At this point, in some embodiments the robotic system 100 may transition to the seated position depicted in FIG. 4F (e.g., based on a command or preconfigured control sequence). For example, instead of immediately initiating release mode, the subject 200 may activate chair mode for extended whole-body support. It is also recognized that in some embodiments, the robotic system 100 may release the subject 200. Accordingly, in some embodiments the robotic system 100 may release the one or more robotic limbs 104 from the subject 200 based on a release command.

[0096] One or more computers can be used to implement such a computational pipeline, using one or more general-purpose computers, such as client devices including mobile devices and client computers, one or more server computers, or one or more database#14424435vlcomputers, or combinations of any two or more of these, which can be programmed to implement the functionality such as described in the example implementations.

[0097] FIGs. 5A, 5B, and 5C depict schematic representations of a methodology for transitioning from a standing position to a sitting position that is similar to that of FIGs. 4A- 4F. However, as seen in FIGs. 5A-5C, in some embodiments, the robotic system 100 may comprise linear actuators 107 which can actuate the seat 102a and / or seat back 102b to guide and / or support the subject 200 between a standing position (e.g., FIG. 5 A) and a seated position (e.g., FIG. 5C).

[0098] Turning to Figure 6, a block diagram of a general-purpose computer is depicted which processes computer programs using a processing system. Computer programs on a general-purpose computer generally include an operating system and applications. The operating system is a computer program running on the computer that manages access to resources of the computer by the applications and the operating system. The resources generally include memory, storage, communication interfaces, input devices and output devices.

[0099] Examples of such general-purpose computers include, but are not limited to, larger computer systems such as server computers, database computers, desktop computers, laptop and notebook computers, as well as mobile or handheld computing devices, such as a tablet computer, handheld computer, smart phone, media player, personal data assistant, audio and / or video recorder, or wearable computing device.

[0100] With reference to Figure 6, an example computer 600 comprises a processing system including at least one processing unit 602 and a memory 604. The computer can have multiple processing units 602 and multiple devices implementing the memory 604. A processing unit 602 can include one or more processing cores (not shown) that operate independently of each other. Additional co-processing units, such as graphics processing unit 620, also can be present in the computer. The memory 604 may include volatile devices (such as dynamic random-access memory (DRAM) or other random-access memory device), and non-volatile devices (such as a read-only memory, flash memory, and the like) or some combination of the two and optionally including any memory available in a processing device. Other memory such as dedicated memory or registers also can reside in a processing unit. Such a memory configuration is delineated by the dashed line 604 in Figure 6. The computer 600 may include additional storage (removable and / or non-removable) including,#14424435vlbut not limited to, solid state devices, or magnetically recorded or optically recorded disks or tape. Such additional storage is illustrated in Figure 6 by removable storage 608 and nonremovable storage 610. The various components in Figure 6 are generally interconnected by an interconnection mechanism, such as one or more buses 630.

[0101] A computer storage medium is any medium in which data can be stored in and retrieved from addressable physical storage locations by the computer. Computer storage media includes volatile and nonvolatile memory devices, and removable and non-removable storage devices. Memory 604 , removable storage 608 and non-removable storage 610 are all examples of computer storage media. Some examples of computer storage media are RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optically or magneto-optically recorded storage device, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices.

[0102] The computer 600 may also include communications connection(s) 612 that allow the computer to communicate with other devices over a communication medium. Communication media typically transmit computer program code, data structures, program modules or other data over a wired or wireless substance by propagating a modulated data signal such as a carrier wave or other transport mechanism over the substance. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal, thereby changing the configuration or state of the receiving device of the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct- wired connection, and wireless media include any non-wired communication media that allows propagation of signals, such as acoustic, electromagnetic, electrical, optical, infrared, radio frequency and other signals. Communications connections 612 are devices, such as a network interface or radio transmitter, that interface with the communication media to transmit data over and receive data from signals propagated through communication media.

[0103] The communications connections can include one or more radio transmitters for telephonic communications over cellular telephone networks, and / or a wireless communication interface for wireless connection to a computer network. For example, a cellular connection, a Wi-Fi connection, a Bluetooth connection, and other connections may be present in the computer. Such connections support communication with other devices, such as to support voice or data communications.#14424435vl

[0104] The computer 600 may have various input device(s) 614 such as a various pointer (whether single pointer or multi-pointer) devices, such as a mouse, tablet and pen, touchpad and other touch-based input devices, stylus, image input devices, such as still and motion cameras, audio input devices, such as a microphone. The computer may have various output device(s) 616 such as a display, speakers, printers, and so on, also may be included. These devices are well known in the art and need not be discussed at length here.

[0105] The various storage 610, communication connections 612, output devices 616 and input devices 614 can be integrated within a housing of the computer or can be connected through various input / output interface devices on the computer, in which case the reference numbers 610, 612, 614 and 616 can indicate either the interface for connection to a device or the device itself as the case may be.

[0106] An operating system of the computer typically includes computer programs, commonly called drivers, which manage access to the various storage 610, communication connections 612, output devices 616 and input devices 614. Such access generally includes managing inputs from and outputs to these devices. In the case of communication connections, the operating system also may include one or more computer programs for implementing communication protocols used to communicate information between computers and devices through the communication connections 612.

[0107] Any of the foregoing aspects may be embodied as a computer system, as any individual component of such a computer system, as a process performed by such a computer system or any individual component of such a computer system, or as an article of manufacture including computer storage in which computer program code is stored and which, when processed by the processing system(s) of one or more computers, configures the processing system(s) of the one or more computers to provide such a computer system or individual component of such a computer system.

[0108] Each component (which also may be called a “module” or “engine” or “computational model” or the like), of a computer system such as described herein, and which operates on one or more computers, can be implemented as computer program code processed by the processing system(s) of one or more computers. Computer program code includes computer-executable instructions and / or computer-interpreted instructions, such as program modules, which instructions are processed by a processing system of a computer. Generally, such instructions define routines, programs, objects, components, data structures,#14424435vland so on, that, when processed by a processing system, instruct the processing system to perform operations on data or configure the processor or computer to implement various components or data structures in computer storage. A data structure is defined in a computer program and specifies how data is organized in computer storage, such as in a memory device or a storage device, so that the data can be accessed, manipulated, and stored by a processing system of a computer.

[0109] As mentioned previously above, in some embodiments, controlling the movement of the robotic system 100 may include determining a motion plan of the one or more robotic limbs 104, the movable base 112, and the one or more linkages 102 of the robotic system using a cost function as described previously above. For example, determining the robotic system’s joint configurations can be formulated as an optimization problem, where the costs and constraints may be designed to achieve this ready -to-support whole-robot configurations. Accordingly, penalties and / or rewards can be used to incentivize and / or prioritize some movements and / or disincentivize other movements (e.g., energy intensive and / or inefficient movements). For example, in some embodiments the mobile base 112 is relatively heavy compared to other portions of the robotic system 100 and therefore may have more inertia. Therefore, movement of the mobile base 112 can be associated with a penalty to increase the cost of moving the mobile base and incentivize moving the arms 104 instead. In some embodiments, the cost function may penalize the one or more robotic limbs being fully extended to incentivize moving the mobile base 112 if the subject moves beyond the reach of the one or more robotic limbs. In some embodiments, achieving a desired pose of the robotic system 100 (e.g., positioning the robotic system 100 to assist a subject) can be rewarded by penalizing an actual position of the robotic system 100 being too far from the desired position. Further detail regarding the motion plan of the robotic system 100 is included in an example below.

[0110] FIG. 7 shows a flow chart depicting a method for controlling the robotic system 100 according to some embodiments. As shown at 702, the method may include obtaining a user pose data. As previously mentioned, the user pose data may be obtained using the one or more sensors 108. In some embodiments, the posture and / or a posture transition of the subject 200 may be determined based at least in part on the user pose data at block 604. This action may be accomplished with the one or processors 110 and any of the methods for determining a posture and / or posture transition of the subject 200 disclosed#14424435vlherein. Then, the robotic system 100 may determine if assistance is needed at 606 based at least in part on the determined posture and / or posture transition of the subject 200. If the robotic system 100 determines that no assistance is currently needed, the robotic system 100 may return to obtaining user pose information. If the robotic system 100 determines that assistance is needed, then it may control a pose of the mobile base 112 based at least in part on the determined posture and / or posture transition at block 608 to proactively improve a stability of the system. For example, the drive system may position the mobile base 112 in a pose to counter a load borne from the subject. The robotic system 100 may then control actuation of the one or more robotic limbs 104 based at least in part on the determined posture and / or posture transition, as shown at 710. Thus, the robotic system 100 may be commanded to engage the subject 200 with the one or more robotic limbs 104 as shown at 612.

[0111] Subsequently, upon contact with the subject 200, the robotic system 100 may optionally update the user pose information based at least in part on pose information collected from one or more limb sensors. In some embodiments, the one or more robotic limbs 104 may include sensors configured to collected updated pose information of the subject 200 upon contact with the one or more robotic limbs 104. For example, the one or more robotic limbs 104 may include at least one four-axis torque force sensor to sense the torque and / or weight applied by the subject 200 when being assisted, though other force and / or torque sensors may also be used. The one or more robotic limbs 104 may include end effectors 114 configured to accurately detect force applied to the one or more robotic limbs. The sensors may be in communication with the one or more processors 110 to determine a posture of the subject 200 based at least in part on the sensed pose information. This updated pose information from the one or more limb sensors may then be used to update the determined posture and / or posture transition at block 714 as noted previously above using any of the methods disclosed for determining a posture of the subject 200. Then, the robotic system 100 may apply an assistive force to the user’s body to improve a stability of the user at 616 and / or aid the user transitioning to a seated position at 716. The previously mentioned pose information may be used, at least in part, to direct the robot on how to assist the subject 200. For example, in one embodiment, the one or more robotic limbs 104 may be operated to apply an assistive force to stabilize the subject’s body, as shown in block 716.#14424435vl

[0112] The robotic system 100 may determine if the user is stable at 716. Blocks 714 - 718 may optionally be repeated until the user is detected to be in a stable position. To provide this functionality, the robotic system may include closed loop control in which the robot may adjust the assistance provided based at least in part on the real-time needs of the user as sensed with real time pose information sensed from the user. For example, the pose information sent from the sensors to the one or more processors 110 may indicate the updated location and / or acceleration of the center mass of the user. This information may be used to direct the one or more robotic limbs 104 on how to continuously guide the user in a desired direction based on the type of sensed posture and / or posture transition. This closed loop system may also be useful for determining when to stop the assistance. The sensors in the one or more robotic limbs 104 may determine when assistance is no longer needed for the user. For example, if a sensed force, torque, or change in position drops below a lower threshold value, the robotic system 100 may disengage the one or more robotic limbs 104 from the subject 200. In some embodiments the robotic system 100 may disengage the user when the one or more processors 110 determine from the posture information that the user is stable. Stability may be defined by a center of mass that is within a predetermined threshold distance from a vertical axis between the feet of the user in a standing configuration or the hips of the user in a sitting or kneeling configuration. This may help to ensure that the user will not fall and / or injure themselves when the robotic system disengages the user.

[0113] Once the subject 200 is stabilized, a voice command or other input can be given to the robotic system 100 to prompt the robotic system to assist the subject 200 in transitioning to the seated positioned or to release the subject. Accordingly, in some embodiments, if a seated position is desired, the robotic system 100 can transition the subject to the seated position at 722 (e.g., see the seated position of FIG. 4F). The robotic system 100 can then be transitioned from the seated position at 722 back to a standing configuration (e.g., see FIG. 4A) while applying an assistive force to the subject at 716. In embodiments where a seated configuration is not desired, the subject 200 can instead prompt the robotic system 100 to remove the assistive force. Accordingly, the robotic system 100 can return to contactlessly monitoring the subject at 602.

[0114] The above method is directed primarily towards an embodiment in which the robotic system 100 assists a user that is in the early stages of falling or is at risk of falling, so the one or more robotic limbs 104 stabilize the user by pulling the user towards the first base#14424435vl102. As previously described, in some embodiments, the robotic system 100 may engage a user that is falling or in an unstable posture. Therefore, in some embodiments, the one or more robotic limbs 104 may be able to apply various different assistive forces to the user such as providing an arm rest, a stabilizing contact force, transitioning the subject between a standing posture and seated posture, and / or any other action that a user may need for support.

[0115] The above method may be implemented by one or more controllers including the one or more processors 110 operatively coupled to the various controllable portions of a robotic system as disclosed herein. The method may be embodied as computer readable instructions stored on non-transitory computer readable memory associated with the at least one processor 110 such that when executed by the one or more processors the robotic system 100 may perform any of the actions related to the methods disclosed herein. Additionally, it should be understood that the disclosed order of the steps is exemplary and that the disclosed steps may be performed in a different order, simultaneously, and / or may include one or more additional intermediate steps not shown as the disclosure is not so limited.

[0116] Example: Stand to Sit Robotic System and Control

[0117] In the following, an exemplary mobile robot system is described that offers quick and safe physical support depending on the user’s state. Described below is the design of one embodiment of interactive mobility robot system for providing postural assistance and catching falls. Also described is a method to generate whole-robot ready-to-catch configurations via optimal control based motion planning.

[0118] Physical therapists dynamically vary their assist level between contactless supervision and contact based support depending on their perception of the patient’s imbalance risk level. Inspired by the lack of user encumbrance with this assist strategy, the robotic support system can be completely detached from the user, make contact only when assistance is needed, and dynamically vary its assistance level based on the person’s predicted risk level.

[0119] Physical therapists are trained to provide varying levels of assistance based on their observation and judgment of the patient’s needs. These assist levels include close supervision, or standby assist, where the therapist’ s hands hover near the body but do not make contact; contact guard assistance in which the therapist contacts the patient to helps steady them; minimal assist, when they provide up to 25% support of the patient’s body weight, up to maximum assist.#14424435vl

[0120] These different levels of assistance can be simplified into two categories:1) Close Supervision - no contact is made with the user, but the support interface follows the user’s movements, staying close by at all times, acting as a “spotter”.2) Contact Assist - the support interface contacts and stabilizes the user’s torso, embracing them within the support arms, and provides varying levels of support to the body.

[0121] Physical therapists exhibit dynamic transitions between contactless supervision modes and contact-based support modes while assisting patients during gait rehabilitation. They provide close supervision to patients by keeping their hands near the patient’s torso while walking closely beside them. If the therapist perceives the patient needs assistance, they transition from hands off “spotting” to hands on support via contacting the torso. If the patient cannot continue, they will try to guide them to a nearby chair or support surface.

[0122] To achieve similar dynamic transitions between off and on support, in some embodiments the robotic system 100 may be able to physically catch and hold a falling person. In some embodiments, this may include bearing roughly two-thirds of the body weight (corresponding to a lean angle of 40 degrees) of a typical 75 kg elderly person. In some embodiments, the robotic system 100 may grasp the body when the user is at risk of falling (e.g., before the user’s tilt angle exceeds 40 deg). In some embodiments, when not grasping the user, the robotic system 100 may follow them closely without making contact. Similar to behaviors exhibited by physical therapists assisting patients undergoing gait rehabilitation, the robotic system 100 can safely and quickly grasp the subject 200, support the whole-body weight in a safe and comfortable position for long periods post-imbalance, and enable the subject 200 to stand up from this supported position on their own once ready. Lastly, the robot may be highly maneuverable and be able to follow behind the user when they walk straight, turn, and make lateral steps (e.g. moving along a kitchen counter). To achieve the aforementioned performance, in some embodiments a robotic system can include 3 major subsystems, including:1) Light weight and compliant arms that enable the robot to quickly and safely embrace the user when imbalanced, with configuration vector qaG Rn"2) A convertible backbone with dual functions of a) mimicking the user’s torso posture by articulating forward to put the arms within reach of the user’s torso while they#14424435vltake different postures, and b) folding into a chair configuration to support a heavy and fragile body for long periods, qsG Rns3) An omnidirectional mobile base that allows the robot to follow behind the user while walking, qb G Rnb

[0123] The configuration vectors for each major subsystem may be combined to give the configuration vector collectively describing this mobile manipulator, q =[ a - s ’ b ]T, where q G R(.na+ns+nbTheroboend effector positions may be computed from q using forward kinematics:G Rnee, and a differential change in end effector position is given by:M^ = J(q)dq (2)

[0124] Similarly, the human has many nhdegrees of freedom, which can be represented by qh G 7?n / 1.We can define a general feature vector describing the human’s balance state as some function of qh. xh = h(qh) (3)

[0125] Control Framework

[0126] This section discusses one exemplary embodiment of a control framework to enable dynamic robot transitions between supervision and assist modes according to some embodiments. Specifically, this section addresses 1) how the appropriate assist level and contact support interface position relative to the body is predicted using imitation learning, 2) the robot joint motion planning optimization, and 3) how the robot behavior modes are changed based on the imitation learning model and user input.

[0127] At each timestep, k, the human balance feature vector xhkis inputted to the imitation learning model, which outputs the desired assist level ALk and end effector position Xeek. The desired end effector position is input to the motion planning optimizer,#14424435vlwhich determines the joint configuration for the next time step Aqk+i These joint commands are sent to the low-level controllers to actuate the robot.

[0128] The robot operates within distinct behavior states or modes, shown in FIG. 8. The 3 primary modes are (contact-less) close supervision 802, contact assist 804, and chair mode 806. By continuously predicting the desired assist level, the imitation learning model enables the robot to dynamically transition from a contactless supervision state at 802 to an in-contact supportive state with the user at 704. The dynamic transitions initiated by the imitation learning model are indicated by the solid line arrows in FIG. 8, while user initiated transitions are indicated by dashed arrows in FIG. 8. The two transient modes include engage mode 808, when the robot moves to make contact with the user’s torso, and release mode 810, when the robot slowly releases the user and returns to close supervision mode.

[0129] Instead of immediately initiating release mode, in some embodiments the user may activate chair mode for extended whole-body support. The convertible backbone can follow a predefined trajectory to fold into a chair configuration, generated by recording a person’s hip and knee angles while sitting, to achieve a natural motion. These modes can provide a structured mechanism to balance proactive support with minimal user encumbrance.

[0130] Imitation Learning for Assist Level Prediction

[0131] This section details an exemplary embodiment of a method for ascertaining when to switch between close supervision and contact assist modes, and how the robot arms are controlled to achieve this dynamic transition according to some embodiments.

[0132] A physical therapist’s behaviors are taken as an expert policy, JT*, that maps the human imbalance feature vector, xht, to an appropriate contact support interface position (relative to the torso) and level of assistive force to provide to the torso. The robot end effector position vector, Xee, corresponds to the support interfaces 3D positions. Similarly, the assist level vector, AL E R2, specifies the level of force, or assistance each robot end effector should provide. While the physical therapist expert policy is not known explicitly, it may be estimated from data. The expert policy is a mapping:#14424435vl

[0133] The assist level at the current time step k is denoted as ALk, and is a continuous variable, AL £ R>0, indicating either zero support or varying levels of hands-on support. With the force, or assist level above a certain threshold level, the corresponding end effector should be in contact with the torso. The threshold at which contact is made can be tuned slightly to achieve the desired level of responsiveness to imbalance.

[0134] The imitation learning model autonomously determines when to transition between close supervision and contact assist modes, tow of the primary behavior modes. Engage and release are transition modes. Once contact assist is achieved, the user directs the robot to release them or transition into a chair to provide longer duration whole-body support.

[0135] The imitation learning model aims to learn the policy that best approximates the expert policy, it* (Equation 5) which describes the difference in the learned policy and expert policy output for the same input feature vector is minimized over all training data points. This supervised learning problem requires a labeled data set given by Equation 6 below.

[0136] Because the imitation learning model is predicting the hand position relative to the user, the position vector can be scaled for users with smaller or larger waists than the one involved in the data collection. A key advantage of this framework compared to existing fall predictors is that no manual labeling of the training data is necessary. The physical therapist’s measured force and hand position indicate the force assist level, AL, and end effector position, Xge, respectively. Low measured force values correspond to low fall risk, and high force values correspond to high fall risk.

[0137] The robot may have redundant degrees of freedom (DOF), so there are multiple possible valid robot configurations for a given end effector position. Note that the#14424435vlimitation learning model outputs the desired end effector position relative to the human, ^eefc+i ’ which is converted to the world frame when used in the optimization,

[0138] Rather than merely tracking the user’s position, the major robot subsystems - the arms, convertible backbone, and mobile base - may be coordinated to assume a ready -to- catch configuration. The problem of determining the robot joint configurations can be formulated as an optimization problem, where the costs and constraints may be designed to achieve this ready-to-support whole-robot configurations. Some simplifying assumptions include that the robot Jacobian was linearized at each iteration k, and the robot moves quasi- statically. These simplifications are reasonable if the optimization runs at a high enough rate with small incremental steps. We may form a quadratic program solving for the incremental change in joint configuration Aqk that gives a desirable future joint configuration qk+i:where, Aqk = qk+i - qk. and the total cost at iteration k is given by:

[0139] The cost function was formulated to achieve desirable ready-to-catch robot configurations across the different behavior modes. The rationale for each term is given here:

[0140] End Effector Position Tracking Penalty: The desired end effector positions should be achieved. Thus, the output joint configurations, qk+i, must minimize any residual error in the resulting end effector position:

[0141] Motion Penalty: The whole movement should be minimized for small changes in the human transverse plane position (x-z plane)#14424435vl

[0142] The first term penalizes a large velocitywhere At is absorbed in W2, andthe second term penalizes a large accelerationwhere At2is absorbed in W3. Usinghigher weights on the mobile base components, Wbase, in W2 and W3, selectively penalizes large mobile base velocities and accelerations, respectively.Arm extension penalty: The arms should avoid singular or extended configurations because the person should not be at the edge of the arms’ reachable set and large moment arms must be avoided during support. However, if the person moves away from the robot quickly, the arms should be able to extend rapidly to intercept the person, p = [pr, pi]T is a vector describing the distance from each shoulder joint to its respective end effector in the robot’s x-z plane. The desirable arm extension range is [min, max] and penalties outside this range are illustrated in FIG. 9 which shows penalties on arm over-extension beyond p - max and under-extension below p - min, where i G {r, 1}. The penalties can be given by:

[0143] In some embodiments, the robotic system 100 may have 11 degrees of freedom (DOF), 3 for the base planar position and orientation, 2 for the convertible backbone and 3 per each arm. 9 DOF are used in the optimization of this example as the robot wrist angle is commanded to always face towards the center of the human torso. However, 11 DOF or other number of DOF can be used depending on the embodiment as the disclosure is not so limited.

[0144] Details on the design of the physical prototype and implementation of the approach are described in this section. In some embodiments, contact forces do not exceed the maximum permissible pressure and force on the user’s abdominal muscles of 140 N / cm2and 180 N, respectively. In some embodiments, the robotic system 100 can support up to 43 kg which is about 1 / 2 of the body weight of a 75thpercentile US individual above age 70 and can catch a person while walking and falling at 2 m / s. In some embodiments, the robotic#14424435vlsystem can be configured to not tip over for the target user weight and most fall scenarios (e.g. when the subject’s lean angle is 40°)

[0145] Having redundant robot DOF may allow dividing conflicting torque and speed requirements to different DOF and may allow the robot to fold into a chair configuration. The robot kinematic model can be expressed as seen in Equation 16 where subscript B is the mobile base frame, located in the top center of the base. The position of the robot end effectors in world coordinates may be given by Equations 17-18.Returning to FIG.1, in some embodiments there may be 3 major components of the robotic system 100: 2 arms 104, the convertible backbone (e.g., plurality of serially connected linkages 102), and the mobile base 112. Each arm 104 may comprise a shoulder and / or elbow joint which may be actuated via 2 harmonic drive motors. In some embodiments, the wrist joint may be controlled via a servo motor. In some embodiments, the convertible backbone can be powered by 3 linear actuators, and the mobile base can be powered by 4 swerve drive motor modules, each containing 2 motors to control wheel direction and speed.

[0146] In some embodiments, a mobile robotic system may comprise two lightweight arms, with na= 6 DOF, a convertible backbone with ns= 2 DOF, and an omnidirectional mobile base with nb = 3 DOF - 2 for planar position, and one for yaw rotation.

[0147] In some embodiments, low inertia robot arms 104 and compliant contact interface can be used to track small changes in the user’s position and quickly and safely grasp them. The 3 degrees of freedom enable torso tracking and aligning the contact interface with the user’s torso. Load cells in the end effectors rated for 50 kg can measure contact forces on the subject’s torso. Both arm motors are collocated at the shoulder joint and the elbow joint is driven via a belt and pulley to reduce arm inertia.#14424435vl

[0148] In some embodiments, the arms are mounted on the second subsystem (e.g., the plurality of serially connected linkages 102). In chair mode, the plurality of serially connected linkages can form the seat 102a and the seatback 102b enabling extended support off the floor and ensuring the structure bears the load without having to power the actuators. Two linear actuators may power the lower frame, and one may power the upper frame. At a max speed of 5 cm / s, the linear actuators can be fast enough to keep up with an elderly person bending over, and with a 445 N rating, can still bear their load and pull them back to a seated position.

[0149] In some embodiments, an omnidirectional, non-holonomic swerve drive enabled the robot to navigate in any direction while maintaining high traction. Each wheel was capable of being driven clockwise / counterclockwise, while simultaneously and independently rotating around the z axis. Compared to Mecanum wheels, this wheel configuration may allow for improved tracking and maneuverability and higher traction. With a linear velocity of 3 m / s, the mobile base 112 can easily follow elderly people walking. In some embodiments, the footprint of the robot is 40 cm2, enabling it to maneuver most home or rehabilitation environments. In some embodiments, the robot weighs 100 kg which may reduce tipping due to a user falling while the robot’s arms are extended.

[0150] With reference to FIG. 10, in some embodiments, the subject 200 and robotic system 100 orientation and position can be measured using an Optitrack motion capture system at 100 Hz. The torso of the subject 200 can be an important area for monitoring stability with the top of the torso being more visible to motion capture cameras. Six reflective markers can be placed on the user’s upper torso to enable measurement of the rigid body frame, OH . Similarly, markers on the top of the convertible backbone 102 of the robotic system 100 were used to determine the robot frame OR. These two frames were used to compute the mobile base frame, OB, and the abdomen frame, OA. The abdomen frame is defined such that yAaxis remains parallel to yH. Each frame of these frames are defined by its position P E R3and orientation R^E SO(3), where i 6 {H, R, A, B}. The human chest frame orientation can also be represented as a unit quaternion■ The center of the mobile base is given by, P , and the base yaw angle is described by 9B.

[0151] FIG. 11 depicts exemplary embodiment of a low-level control architecture 1100 of the mobile base 112 according to some embodiments. In the depicted embodiment, the low-level control architecture 1100 can control a speed of the robotic system 100 using#14424435vlone or more proportional, integral, derivative, and feedforward gains according to some embodiments (e.g., using the PID controllers 1110). As seen in FIG. 11, a high level planner 1110 outputs a desired robot base pose to a PID controller 1112 and a perception system 1114 outputs a measured robot base pose to the PID controller 1110. The PID controller 1110 then determines a desired robot base velocity which is output to a swerve drive inverse kinematics block 1116. The swerve drive inverse kinematics block 1116 then outputs desired wheel speeds to a PID controller 1118 which transmits a motor command to one or more wheel modules 1120. As a result, the mobile base 112 of the robotic system 100 can be controlled.

[0152] FIG. 12 depicts one embodiment of a control architecture 1200 of the robotic system 100 according to some embodiments. In some embodiments, the control architecture 1200 may comprise learning model 1210 which continuously predicts the desired level of assistance to provide close and / or supervision or contact assist. The robot state in the Behavior Modes finite-state machine 1220 (FSM) may be updated based on this prediction and the user’s input in the form of a voice command. The voice command at time step k is denoted as Vk G V, where V = {“release me”, “sit”, “stand”} is the set of valid voice commands.

[0153] The desired end effector position predicted from the trained imitation learning model 1110, X'e. may be updated in the Behavior Modes FSM 1120 depending on the current robot state. The updated position is denoted as X’e. The joint motion planning optimization determines suitable robot configurations, qk+i, that are sent to the low level controllers at 50 Hz. Measurements include the previously mentioned motion capture values, robot arm and convertible backbone angles via encoders, and the normal forces on the robot end effectors through embedded load cells.

[0154] FIGs. 13A-13C depict robot motion planning optimization performance and the effect of base weight changes on relative joint contribution to the right end effector x displacement for a predefined end effector trajectory. Fig. 13 A shows the reference end effector position trajectory in the forward direction X^ , which does not stray far from the initial robot position in phase 1), but increases quickly in phase 2), moving the end effectors far forward from the initial robot position. In phase 1, the desired end effector locations are within the arm workspace even if the mobile base and convertible backbone remain stationary. In phase 2, the desired end effector positions would be out of the arm workspace in the x direction if the mobile base did not move. In FIGs. 13B-13C, the cost function weight#14424435vlpenalties were tuned, using predefined end effector position trajectories in simulation and validated on the robot hardware. Fig. 13B shows the resulting distribution of the robot DOF motion for changes in the x position of the right EE for different penalty values of wbase. A penalty value of wbase = 500 was selected as it was the first to produce zero mobile base motion in phase 1 as desired, Axb. FIG. 13C shows the change in the distribution of robot joint DOF motion from phase 1 to phase 2 with this selected weight value. As desired, during phase 2, the mobile base motion accounts for most of the change in the Xposition of the right end effector, AXeer.

[0155] FIGs. 14A-14C depict graphs of robot motion planning optimization performance having joint trajectories output from optimization using the optimized weights and predefined end effector trajectories both in simulation and on the hardware according to the depicted embodiment.

[0156] In the scenarios tested in which the participant walked away from the robotic system, the robotic system was able to follow behind and keep up with the user. During this motion, the end effectors were also positioned at reasonable proximity to the user. The arms avoided full extension most of the time, remaining at least slightly bent, putting them in a better configuration to support the user if needed. The robot was also successfully able to guide the user into a sitting position while folding itself into a chair and bear the user’s entire weight comfortably.

[0157] After selecting desired weight penalty values for the cost function terms, the optimization output was compared on hardware to the simulation results using the same prerecorded end effector (EE) position trajectories as input, and the same starting robot configuration as input. The results for this single test case are shown in FIGs. 14A-14C, where output arm joint angle trajectory are in FIG. 14A. In FIG 14A, 1401 is the simulated right shoulder trajectory, 1402 is the real right shoulder trajectory, 1403 is the simulated right elbow trajectory, 1404 is the real right elbow trajectory, 1405 is the simulated left shoulder trajectory, 1406 is the real left shoulder trajectory, 1407 is the simulated left elbow trajectory, 1408 is the real left elbow trajectory. The resulting convertible backbone joint angle trajectories are in FIG. 14B where 1409 is the back lower simulated, 1410 is the back lower real, 1411 is the back upper simulated, 1412 is the back upper real, 1413 is the base angled simulated, 1414 is the base angle real. The mobile base motion is shown in FIG. 14C where 1415 is the simulated mobile base motion and 1416 is the real mobile base motion. There is a#14424435vlslight phase delay due to using pure feedback control in the low level controllers, but otherwise the simulation and real results match very closely.

[0158] The above-described embodiments of the technology described herein can be implemented in any of numerous ways. For example, the embodiments may be implemented using hardware, software, or a combination thereof. When implemented in software, the software code can be executed on any suitable processor or collection of processors, whether provided in a single computing device or distributed among multiple computing devices. Such processors may be implemented as integrated circuits, with one or more processors in an integrated circuit component, including commercially available integrated circuit components known in the art by names such as CPU chips, GPU chips, microprocessor, microcontroller, or co-processor. Alternatively, a processor may be implemented in custom circuitry, such as an ASIC, or semicustom circuitry resulting from configuring a programmable logic device. As yet a further alternative, a processor may be a portion of a larger circuit or semiconductor device, whether commercially available, semi-custom or custom. As a specific example, some commercially available microprocessors have multiple cores such that one or a subset of those cores may constitute a processor. Though, a processor may be implemented using circuitry in any suitable format.

[0159] Further, it should be appreciated that a computing device including one or more processors may be embodied in any of a number of forms, such as a rack-mounted computer, a desktop computer, a laptop computer, or a tablet computer. Additionally, a computing device may be embedded in a device not generally regarded as a computing device but with suitable processing capabilities, including a Personal Digital Assistant (PDA), a smart phone, tablet, or any other suitable portable or fixed electronic device.

[0160] Also, a computing device may have one or more input and output devices. These devices can be used, among other things, to present a user interface. Examples of output devices that can be used to provide a user interface include display screens for visual presentation of output and speakers or other sound generating devices for audible presentation of output. Examples of input devices that can be used for a user interface include keyboards, individual buttons, and pointing devices, such as mice, touch pads, and digitizing tablets. As another example, a computing device may receive input information through speech recognition or in other audible format.#14424435vl

[0161] Such computing devices may be interconnected by one or more networks in any suitable form, including as a local area network or a wide area network, such as an enterprise network or the Internet. Such networks may be based on any suitable technology and may operate according to any suitable protocol and may include wireless networks, wired networks or fiber optic networks.

[0162] Also, the various methods or processes outlined herein may be coded as software that is executable on one or more processors that employ any one of a variety of operating systems or platforms. Additionally, such software may be written using any of a number of suitable programming languages and / or programming or scripting tools, and also may be compiled as executable machine language code or intermediate code that is executed on a framework or virtual machine.

[0163] In this respect, the embodiments described herein may be embodied as a computer readable storage medium (or multiple computer readable media) (e.g., a computer memory, one or more floppy discs, compact discs (CD), optical discs, digital video disks (DVD), magnetic tapes, flash memories, RAM, ROM, EEPROM, circuit configurations in Field Programmable Gate Arrays or other semiconductor devices, or other tangible computer storage medium) encoded with one or more programs that, when executed on one or more computers or other processors, perform methods that implement the various embodiments discussed above. As is apparent from the foregoing examples, a computer readable storage medium may retain information for a sufficient time to provide computer-executable instructions in a non-transitory form. Such a computer readable storage medium or media can be transportable, such that the program or programs stored thereon can be loaded onto one or more different computing devices or other processors to implement various aspects of the present disclosure as discussed above. As used herein, the term "computer-readable storage medium" encompasses only a non-transitory computer-readable medium that can be considered to be a manufacture (i.e., article of manufacture) or a machine. Alternatively or additionally, the disclosure may be embodied as a computer readable medium other than a computer-readable storage medium, such as a propagating signal.

[0164] The terms “program” or “software” are used herein in a generic sense to refer to any type of computer code or set of computer-executable instructions that can be employed to program a computing device or other processor to implement various aspects of the present disclosure as discussed above. Additionally, it should be appreciated that according to one#14424435vlaspect of this embodiment, one or more computer programs that when executed perform methods of the present disclosure need not reside on a single computing device or processor, but may be distributed in a modular fashion amongst a number of different computers or processors to implement various aspects of the present disclosure .

[0165] Computer-executable instructions may be in many forms, such as program modules, executed by one or more computers or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Typically the functionality of the program modules may be combined or distributed as desired in various embodiments.

[0166] The embodiments described herein may be embodied as a method, of which an example has been provided. The acts performed as part of the method may be ordered in any suitable way. Accordingly, embodiments may be constructed in which acts are performed in an order different than illustrated, which may include performing some acts simultaneously, even though shown as sequential acts in illustrative embodiments.

[0167] Further, some actions are described as taken by a “user.” It should be appreciated that a “user” need not be a single individual, and that in some embodiments, actions attributable to a “user” may be performed by a team of individuals and / or an individual in combination with computer-assisted tools or other mechanisms.

[0168] While the present teachings have been described in conjunction with various embodiments and examples, it is not intended that the present teachings be limited to such embodiments or examples. On the contrary, the present teachings encompass various alternatives, modifications, and equivalents, as will be appreciated by those of skill in the art. Accordingly, the foregoing description and drawings are by way of example only.

[0169] While several embodiments have been described and illustrated herein, those of ordinary skill in the art will readily envision a variety of other means and / or structures for performing the functions and / or obtaining the results and / or one or more of the advantages described herein, and each of such variations and / or modifications is deemed to be within the scope of the present disclosure. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemples and that the actual parameters, dimensions, materials, and / or configurations will depend upon the specific application or applications for which the teachings of the present invention is / are used. Those skilled in the art will recognize, or be#14424435vlable to ascertain using no more than routine experimentation, many equivalents to the specific embodiments of the invention described herein. It is, therefore, to be understood that the foregoing embodiments are presented by way of example only and that, within the scope of the appended claims and equivalents thereto, embodiments may be practiced otherwise than as specifically described and claimed. Disclosed embodiments are directed to each individual feature, system, article, material, kit, and / or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and / or methods, if such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent, is included within the scope of the present disclosure.

[0170] Exemplary Embodiments

[0171] Embodiment 1, a system for mechanical support of a subject comprises: a vertical exoskeleton comprising a set of three or more rectangular panels, wherein the panels are connected to each other by motorized hinges; a pair of arms, wherein each arm is connected to the vertical support by a motorized joint, wherein each arm comprises two or more segments separated by motorized joints, and wherein each arm comprises an inflatable cuff or a foam covering to protect the subject from injury; an ability to fold into a seat for the subject; a compact mobile base on four wheels, wherein the base comprises a front region connected to the vertical support a motor to supply motive power to at least two of the four wheels; and a vertical support for the seat formed by folding the vertical support.

[0172] Embodiment 2, the system of embodiment 1 further comprising a sensory system configured to (continuously, periodically) track a location of the subject.

[0173] Embodiment 3, the system of embodiment 1 further comprising a computer comprising a processor, wherein sensory system is an input into the computer.

[0174] Embodiment 4, the system of embodiment 1 further comprising a power supply, wherein the power supply enables the computer to control the joints, hinges, and wheels.

[0175] Embodiment 5, the system of embodiment 1 wherein the exoskeleton actively tracks and mimics the subject’s posture.

[0176] Embodiment 6, the system of embodiment 1 wherein the base continually moves to situate itself behind the subject and provide support as needed.

[0177] Embodiment 7, the system of embodiment 1 wherein the base optionally comprises a pair of wheels that extend to provide additional stability and support as needed.#14424435vl

[0178] Embodiment 8, the system of embodiment 1 wherein each of the arms further comprises a brace mounted on the vertical exoskeleton, wherein the brace is configured to provide mechanical strength to the arm.

[0179] Embodiment 9, the system of embodiment 7 wherein the arms are configured to bear a vertical load created by the subject.

[0180] Embodiment 10, the system of embodiment 1 wherein in the event of a fall, the robotic arms are located closely behind the subject and are configured to quickly and gently grasp the subject to prevent the fall.

[0181] Embodiment 11, the system of embodiment 1 wherein the vertical exoskeleton folds into a chair and is connected to the vertical support of the compact mobile base.

[0182] Embodiment 12, the system of embodiment 1 wherein the vertical exoskeleton is configured to continually guide the subject through a predetermined safe stand-to-sit trajectory based under control by the computer.

[0183] Embodiment 13, the system of embodiment 1 wherein the vertical exoskeleton further comprises a scissor linkage with an extension spring to guide and slow descent of the subject to a sitting position.

[0184] Embodiment 14, a method of supporting a subject using the system of anyone of the embodiments 1-13.

[0185] Embodiment 15, a clinic for physical therapy comprising the system of any one of embodiments 1-13.

[0186] Embodiment 16, a computer system for controlling the support system of any one of embodiments 1-13, the computer system comprising a processing system, computer storage accessible to the processing system, and computer program instructions encoded on the computer storage, wherein when the computer program instructions are processed by the processing system, and the computer system is configured to define data structures in the computer storage representing the position and location of the subject, and execute a computer program applied to the data structures to assist (provide mechanical support to) the subject.

[0187] Embodiment 17, the computer system of embodiment 16 further comprising a means of tracking sensory signals from the sensory system of the support system and to (continuously, periodically) track a location of the subject.#14424435vl

[0188] Embodiment 18, the computer system of embodiment 16 wherein the computer program was generated by machine learning.

[0189] Embodiment 19, a computer program product comprising computer storage and computer program instructions encoded on the computer storage, wherein the computer program instructions, when processed by a processing system of a computer, causes the computer to perform the method of embodiment 14 or implement the computer system of any one of embodiment 16-18.#14424435vl

Claims

CLAIMS1. A robotic system configured to assist a subject, the robotic system comprising: a plurality of serially connected linkages; a plurality of actuators configured to move the plurality of serially connected linkages between a standing support configuration and a seated support configuration; and one or more moveable robotic limbs extending from one or more of the plurality of serially connected linkages, the one or more moveable robotic limbs configured to be engaged with a body of the subject.

2. The robotic system of claim 1 further comprising: one or more sensors configured to sense pose information of the subject; and one or more processors configured to: determine a posture and / or a posture transition of the subject based at least in part on the sensed pose information; control the one or more moveable robotic limbs to be engaged with the subject’s body based at least in part on the determined posture and / or posture transition of the subject while the plurality of serially connected linkages are in the standing support configuration; and control the plurality of actuators to transition the plurality of serially connected linkages from the standing support configuration to the seated support configuration.

3. The robotic system of claim 2, wherein the sensed pose information includes one or more selected from: a position, velocity, and / or acceleration of a center of mass of the subject; a ground reaction force between feet of the subject and the ground; and a whole body angular momentum of the subject.

4. The robotic system of claim 2, wherein the one or more sensors comprises one or more of a camera, an inertial measurement unit, an accelerometer, and / or a distance sensor.#14424435vl5. The robotic system of claim 2, further comprising a mobile base, wherein the plurality of serially connected linkages are connected to the mobile base, and wherein the mobile base is configured to maintain a predetermined pose relative to the subject during operation.

6. The robotic system of claim 5, wherein the one or more processors are configured to control the mobile base and the plurality of actuators to maintain a pose of the plurality of serially connected linkages relative to the body of the subject.

7. The robotic system of claim 6, wherein the one or more processors are configured to control the mobile base and the plurality of actuators by minimizing a cost function.

8. The robotic system of claim 1, wherein the plurality of serially connected linkages have one or more joints configured to be aligned with a subject’s hip and / or knee in one or more configurations.

9. The robotic system of claim 1, wherein the one or more moveable robotic limbs comprise a cushioned end effector configured to contact the subject.

10. The robotic system of claim 1, wherein a first linkage of the plurality of serially connected linkages is a seat configured to support the subject in the seated support configuration.

11. The robotic system of claim 1, wherein a second linkage of the plurality of serially connected linkages is a seatback configured to support the subject in the seated support configuration.

12. A method of assisting a subject with a robotic system, the method comprising: monitoring a posture of the subject; predicting a need for assistance based on the posture of the subject; engaging the subject with one or more robotic limbs of the robotic system connected to a plurality of serially connected linkages; and#14424435vltransitioning the plurality of serially connected linkages from a standing support configuration to a seated support configuration.

13. The method of claim 12, wherein the robotic system contactlessly monitors the posture of the subject.

14. The method of claim 12, further comprising tracking the subject to maintain the one or more robotic limbs within reach of the subject.

15. The method of claim 14, further comprising: maintaining a back structure of the plurality of serially connected linkages in an at least partially vertical orientation when following the subject; and articulating the back structure away from the vertical orientation to align the back structure with the subject’s posture during a fall.

16. The method of claim 15, further comprising transitioning the subject to a seated position when the plurality of serially connected linkages transition from the standing support configuration to the seated support configuration.

17. The method of claim 16, further comprising releasing the one or more robotic limbs from the subject based on a release command.

18. The method of claim 12, wherein predicting a need for assistance is based at least in part on one or more selected from: a position, velocity, and / or acceleration of a center of mass of the subject; a ground reaction force between feet of the subject and the ground; and a whole body angular momentum of the subject.

19. The method of claim 12, further comprising maintaining a movable base connected to the plurality of serially connected linkages in a predetermined pose relative to the subject during operation.#14424435vl20. The method of claim 19, further comprising controlling movement of the base and the plurality of serially connected linkages using a cost function.#14424435vl

Images