269 results about "Multi joint" patented technology

The invention relates to the technical field of data analysis, and discloses a data analysis system for multi-joint exercise rehabilitation monitoring. The system collects three-dimensional motion data, myoelectricity activity signals and spatial position data of multiple joints in real time through a multi-mode sensor array. The system comprises a data acquisition module, a preprocessing module, a space-time analysis module and a result output module. The preprocessing module is used for carrying out noise removal, normalization and feature extraction on the original data; the space-time analysis module constructs a monitoring model based on a graph space-time network, and analyzes space-time characteristics of multi-modal data through dynamic joint relation modeling by adopting an intelligent chip. And the result output module generates a visual report including exercise coordination evaluation, injury risk prediction and rehabilitation progress judgment, and feeds back the visual report to the rehabilitation equipment in real time. Besides, the system also has distributed storage and real-time feedback functions, the accuracy and efficiency of rehabilitation monitoring are improved, and the problems of single data processing and inaccurate spatial-temporal feature capture in the prior art are solved.

The invention discloses a multi-joint robot system fault diagnosis method based on hydraulic drive, belongs to the technical field of multi-joint robot fault diagnosis, and aims to solve the problems that single parameter judgment is prone to misjudgment, associated part abnormity traceability is difficult, and complex environments and multi-stage operation are difficult to adapt. The method comprises the following steps: dividing operation stages, identifying key parts, collecting operation and environment parameters, and storing and establishing a dynamic association library according to an association mode; environment intervals are divided, a model containing a single parameter and a collaborative benchmark is constructed by combining the operation stage and the environment intervals, and the model is matched through environment abnormity diagnosis; comparing a current parameter with the model, diagnosing and positioning an abnormal part, and analyzing an abnormal parameter proportion, a correlation coefficient and a collaborative deviation degree to judge a potential fault; and if yes, establishing a correlation graph and a fault influence chain, and identifying an abnormal source. And multi-dimensional accurate diagnosis is realized, misjudgment is reduced, the source of abnormities is efficiently traced, and the fault diagnosis adaptability under a complex environment and multi-stage operation is improved.

The invention relates to the technical field of mechanical arm operation monitoring, in particular to a multi-joint mechanical arm operation track intelligent monitoring system based on artificial intelligence, which comprises a mechanical arm track monitoring platform, a mechanical arm operation unit, a track generation unit, a joint track tracking unit, an interference matching unit, a track action analysis unit and an offset management unit, according to the method, on the premise that the moving track is determined, whether the joint position coordinates of the multi-joint mechanical arm are accurate or not is preliminarily analyzed, on the premise that the joint position coordinates are accurate, whether the track in the joint moving step process is normal or not is analyzed in a deep mode, and analysis is conducted in combination with vibration interference factors of the multi-joint mechanical arm; according to the method, the moving trajectory coincidence degree is reasonably analyzed, analysis is carried out according to the moving trajectory coincidence degree, the moving trajectory standard is known, the moving trajectory is adjusted reasonably and specifically according to the information feedback condition, and the accuracy and stability of the moving trajectory of the multi-joint mechanical arm are improved.

The embodiment of the invention discloses a trajectory determination method of a multi-joint robot and electronic equipment, and belongs to the technical field of robot control and kinematics. The trajectory determination method of the multi-joint robot comprises the steps that real-time pose information of each joint of the robot is acquired, and the following deviation of each joint is determined according to the real-time pose information and an expected pose; determining the coupling deviation of each joint according to the following deviation of each joint and the influence weight of each joint; and determining a compensation value of each joint based on the coupling deviation of each joint, and inputting the compensation value into a speed control loop of each joint so as to adjust the motion state of the robot. Through calculation and application of the compensation value, the speed output of each joint is dynamically adjusted, so that the overall movement of the robot gradually tends to a synchronous state, thereby reducing the deformation of a tail end track and improving the operation precision.

The invention relates to the technical field of rehabilitation training, in particular to a rehabilitation training method and system integrating a rehabilitation robot and a cloud platform. Comprising the following steps: constructing a standardized motion track data set; joint time sequence features are extracted, coordination deviation in the multi-joint coordination process is analyzed, time sequence coordination deviation distribution is determined, and when deviation exceeds a preset range, an abnormal deviation track and a compensation behavior mode are recognized; generating a personalized training protocol scheme in combination with the compensatory behavior pattern and patient personalized data, and obtaining an optimized motion guidance path through multi-joint collaborative path simulation and parameter correction; training feedback indexes are extracted based on the motion guidance path, the training effect is judged, rehabilitation robot control parameters are dynamically updated, and a continuously optimized function recovery path is formed. The problems that in existing rehabilitation training, multi-joint collaborative evaluation is insufficient, and a training scheme is difficult to dynamically adapt are solved, and intelligentization, individualization and continuous optimization of the rehabilitation training process are achieved.

The invention provides a manual control instrument for a multi-joint endoscope. The multi-joint endoscope manual control instrument comprises an operation clamp, a control mechanism and a manual control assembly. The control mechanism comprises a machine shell and a winding wheel assembly. Two winding wheel assemblies are movably installed on the surface of the machine shell and are oppositely and perpendicularly arranged, each winding wheel assembly is provided with two traction ends which are oppositely pulled, the traction ends are connected with the joint portion of the operation clamp after being guided in a direction changing mode, and the two winding wheel assemblies are matched in a staggered mode to pull the operation clamp to be bent in the four directions. The manual control assembly comprises a positioning ball, a control chain and a handle; the middle shaft end of the handle is connected with a positioning ball, the positioning ball is movably embedded in the machine shell, two control chains are installed outside the handle, and the two control chains drive the two winding wheel assemblies in a one-to-one correspondence mode. The winding wheel assembly is driven through rotation of the handle, so that the operation clamp is bent in the rotation direction of the handle, no counter-acting force needs to be applied, unexpected displacement is avoided, the operation precision and the operation safety are improved, and the overall size of the equipment is small.

The invention discloses a bionic ankle joint and an artificial limb, the bionic ankle joint comprises an ankle joint base and a sole mechanism, and the ankle joint base is used for being connected with a leg component; the sole mechanism comprises a front sole component, a rear sole component and at least one elastic piece, the rear sole component is rotationally connected with the ankle joint base, the front sole component is rotationally connected with the rear sole component, one end of the elastic piece is connected with the rear sole component, and the other end of the elastic piece is connected with the front sole component; the elastic component is used for providing elastic restoring force when the front sole component rotates relative to the rear sole component. The sole fitting degree is improved through multi-joint linkage, the gait stability is enhanced, the additional burden caused by uneven stress is avoided, energy recycling is achieved through the elastic piece, energy consumption is reduced, meanwhile, the pedaling effect is improved through elastic assistance in the pedaling stage, the motion characteristic of the bionic ankle joint is closer to the natural state of the human body, and the mechanical performance of the bionic ankle joint is improved. And the matching degree of equipment and human motion characteristics is improved.

The invention discloses an upper limb multi-dimensional exercise trainer which is characterized in that a low-position limiter and a position control and resistance adjustment ball table are connected to a stand column in a sleeving manner, the position of the position control and resistance adjustment ball table on the stand column is adjusted through the low-position limiter, a ball shaft is mounted on the position control and resistance adjustment ball table, a sliding rod is arranged on the ball shaft in a penetrating manner, and an adjustable anti-falling device is arranged on the sliding rod; the sliding rod is connected with a damping rotating sleeve and a lock sleeve, and the lock sleeve is detachably connected with a single handle or an adjustable damping bearing seat; a sliding rod, a ball pair, a universal joint mechanism and a resistance adjusting mechanism are connected with a bearing connector, a damping-adjustable bearing seat is connected with the bearing connector, the bearing connector is connected with a Tai Chi ball or a double-shaft resistance adjusting universal joint, and the double-shaft resistance adjusting universal joint is connected with a Tai Chi wheel or a double-handle bar, and the Tai Chi wheel, the Tai Chi ball, the single-handle bar and the double-handle bar are connected through cooperation of the sliding rod, the ball pair, the universal joint mechanism and the resistance adjusting mechanism and a modular interface. Multi-azimuth and multi-angle movement operation is realized, and the user can realize coordinated actions such as front, back, left, right, turning and the like of the upper limbs and rehabilitation and exercise of multiple muscle groups and multiple joints of the whole body during exercise and rehabilitation activities.

The invention belongs to the technical field of six-axis robots, and discloses a method for predicting robot joint friction based on an improved PINN principle and a LuGre model, and the method specifically comprises the following steps: 1, generating a robot excitation track, and collecting the positions, speeds and currents of six joints of a robot; 2, current estimation torque of each joint of the robot is calculated according to the current, and a friction force-speed-displacement mapping of the joints of the robot is obtained; 3, constructing a friction model of the robot based on the improved PINN principle and the LuGre model; and 4, designing a double-neural network learning strategy of the robot friction model. According to the method, the improved physical information neural network PINN and the LuGre model are fused, the multi-joint coupling effect of the six-axis robot and the friction characteristic in the full-speed range can be considered at the same time, accurate prediction of the joint friction force of the six-axis robot is achieved, the prediction precision is improved, and the prediction efficiency is improved. And the problem of physical information loss caused by model simplification is also avoided.

A system includes a chamber, a robot within the chamber, the robot including a plurality of links. The system further includes a vertically oriented sensor within the chamber, the vertically oriented sensor to detect a presence of one or more of the plurality of links. The system further includes a controller, to perform for each link to cause the robot to move the link through a field of view of the vertically oriented sensor. The controller further determines a zero horizontal position for the link based on the position of the link at which the link was detected by the vertically oriented sensor. The controller further automatically calibrates the robot within the chamber based on the zero horizontal position determined for each of the plurality of links.

The invention provides a mechanism wear characteristic analysis method considering multi-joint correlation, and relates to the technical field of mechanical wear analys.The method comprises the steps that a direct correlation intensity matrix is determined according to time sequence wear data of all joints of a mechanism, and a wear influence directed graph is generated; in the wear influence directed graph, obtaining all influence transmission paths from any joint to another joint; constructing a first prediction model and a second prediction model by taking a target joint influencing the tail end of the transmission path as a verification object; if the prediction precision of the second prediction model is greater than the prediction precision of the first prediction model, determining that the influence transmission paths are effective, generating an effective path set according to all the effective influence transmission paths, and analyzing the wear characteristics of each joint or the overall mechanism based on the overall mechanism wear correlation network model; the problems that the analysis error is large and the system-level wear evolution rule cannot be reflected due to neglect of joint correlation in a traditional method are effectively solved.

The invention relates to a sports competition training action deviation detection and immediate correction method. The method comprises the following steps: collecting multi-joint dynamic data in a training process; on the basis of a preset inertial conduction continuity criterion, inertial change among all joints of the body is analyzed, and when it is detected that inertial conduction of any joint node is interrupted or an impact value is lower than a threshold value, the joint node is identified as a trigger point of action chain interruption; performing causal priority judgment on the action deviation based on the identified trigger point, determining whether the deviation is a dominant deviation or a subordinate deviation caused by an upstream joint, and if the deviation is the subordinate deviation, tracing an upstream cause and repositioning an intervention target; judging whether the current training stage is in a correction window stage suitable for feedback or not for the deviation which is confirmed to be intervened, and if not, delaying feedback output; and in the window period, trend judgment is performed on the deviation direction, if the deviation causes negative technical degradation, correction feedback is output, and if the deviation trend has positive evolution potential, the deviation is marked as acceptable deviation and is not corrected.

The present invention discloses a simplified multi-joint manipulator friction parameter identification method based on the Stribeck model. The method process is as follows: the multi-joint manipulator system is split into multiple single-joint subsystems; a friction force model of each subsystem is constructed; for each subsystem, the driver is used to drive the subsystem to sample its angle, angular velocity, and torque; the sampled angular velocity is filtered, and the angular acceleration is obtained using a Butterworth filter; the angle, angular velocity, torque, and angular acceleration are substituted into the model of the single-joint subsystem to calculate the friction torque, and the friction parameters are identified based on the least squares method; the obtained friction parameters are used as the friction model parameters of the multi-joint manipulator system. The simplified multi-joint manipulator friction parameter identification method based on the Stribeck model proposed in the present invention can reduce the computational complexity of the multi-joint manipulator system friction parameter identification and can provide accurate modeling of the manipulator friction.

Methods, systems, and / or apparatuses are provided for providing multi-joint assistance for and / or resistance against leg movement of a user. The assistance may be provided to a paretic leg or a prosthetic leg of the user. Kinematic data associated with the paretic or prosthetic leg of the user may be received. The data may include one or more of velocity data, position data, orientation data, or acceleration data for differing portions of the paretic or prosthetic leg. A current phase of a gait motion for the paretic or prosthetic leg may be determined based on the kinematic data. One or more of electrical stimuli or motorized assistance or resistance may be provided to the paretic leg, prosthetic leg, or the remaining portion of the amputated leg based on the current phase of the gait motion of the paretic or prosthetic leg.

The invention discloses an action normalization real-time evaluation method, system and device and a storage medium, and the method comprises the steps: obtaining human body action image data, and carrying out the preprocessing of the data, and obtaining a preprocessed human body action image; performing skeleton point detection on each frame of preprocessed human body action image by using a pre-trained human body posture estimation model to obtain two-dimensional coordinate information of main joints of a human body in each frame of image, and constructing a time sequence skeleton key point sequence; and a time sequence feature analysis algorithm is adopted to analyze the time sequence skeleton key point sequence, multi-joint angle normalization and dynamic fluency evaluation is carried out, and a joint correction suggestion is customized according to an evaluation result. According to the method, quantitative analysis and objective scoring of motion normalization and fluency can be realized without additional hardware equipment, so that the practicability of the evaluation system in scenes of physical education, rehabilitation training, fitness guidance and the like is remarkably improved.

The invention relates to the technical field of robots, and particularly discloses a multi-joint robot fault diagnosis system and method based on a fractional order neural network, the fractional order neural network is adopted, and through the synergistic effect of a fractional order convolution layer, a fractional order pooling layer and a fractional order ReLU function, compared with an integer order model, the fault diagnosis efficiency of the multi-joint robot is improved. According to the method, the non-linear and non-stationary feature capture capability of multi-joint vibration signals is remarkably enhanced, early weak fault features can be accurately extracted, the diagnosis accuracy of early faults such as gear tooth micro pitting corrosion and bearing clearance abnormity is improved, and the weak fault recognition capability is enhanced; a temporary decision maker mechanism under a distributed group learning framework retains the advantage of low communication cost, and meanwhile, through joint loss function optimization and dynamic weight distribution, data privacy protection and model training efficiency are considered, the communication cost is reduced, the training period is shortened, and the system performance is improved. The core requirements of industrial scenes for high precision, low time delay and strong privacy of fault diagnosis are met.

The invention discloses a lower limb multi-joint torque intelligent prediction method and related equipment, and relates to the technical field of joint torque prediction.The method comprises the steps that original surface electromyography sEMG, kinematics data and ground reaction data of a subject under different lower limb movements are collected; kinematics data and ground reaction force data are used as input, and multi-degree-of-freedom angle data and moment data of three joints of the lower limb are obtained through inverse kinematics and inverse dynamics calculation; constructing a lower limb multi-joint torque prediction model through a deep learning technology, and performing model training by using the training set; and inputting the test sample set into the trained lower limb multi-joint torque prediction model to obtain a joint torque prediction result of the subject. According to the method, the problems of low joint torque prediction precision, high calculation cost and the like in the prior art are solved, the method has the advantages of being easy to implement, high in generalization, capable of processing large-scale data and the like, and prediction results are expected to be applied to three-dimensional compliance and modular control of the exoskeleton robot.

The invention relates to an upper limb multi-joint training device, and belongs to the technical field of rehabilitation medical instruments. The device comprises a main motion platform, a driven execution terminal and a connecting mechanism, the main motion platform is a multi-degree-of-freedom industrial mechanical arm and is used for driving the upper limbs of a user to complete three-dimensional space compound motion of shoulder and elbow joints; the connecting mechanism is arranged between the tail end of the main motion platform and the driven execution terminal and is used for detachably mounting the driven execution terminal at the tail end of the main motion platform; the driven execution terminal comprises three rotating joints which are sequentially connected in series, and the three rotating joints respectively provide a rotating degree of freedom to correspondingly realize the flexion and extension movement of the wrist joint, the radial ulnar deviation movement and the pronation and supination movement of the forearm. According to the invention, large-range collaborative movement of shoulder and elbow joints and full-degree-of-freedom refined training of wrist joints can be realized at the same time, comprehensiveness of rehabilitation training is improved, and the device is suitable for clinical rehabilitation training of patients with upper limb movement dysfunction.

The utility model provides a joint assembly and a horizontal multi-joint robot, and the joint assembly comprises a housing, a sealing installation cavity is arranged in the housing, and the housing is provided with an installation hole and a first through hole which are communicated with the sealing installation cavity; one end of the working shaft is mounted in the sealed mounting cavity, the other end of the working shaft extends out of the mounting hole, and the working shaft can slide in the axial direction of the working shaft relative to the shell; the sealing module is mounted at the mounting hole and used for sealing a gap between the inner side wall of the mounting hole and the working shaft; and the dustproof ventilation valve group is mounted at the first through hole, and the dustproof ventilation valve group can enable gas between the interior and the exterior of the shell to flow and can prevent dust between the interior and the exterior of the shell from flowing. According to the structure, the first through hole and the dustproof ventilation valve set are additionally arranged on the joint assembly, so that pressure balance inside and outside the joint assembly can be ensured, dust inside the joint assembly is prevented from flowing out, and the protection effect of the joint assembly is ensured.

A robot includes a torso structure, a head structure, robotic arms, gripper structures, and a chassis driving structure. The torso structure includes a lower leg assembly, a thigh assembly, and a thoracic cavity assembly. A first torso motor, a second torso motor, and a third torso motor enable a multi-joint rotation within a plane formed by a first direction and a second direction. A fourth torso motor drives the thoracic cavity assembly to rotate relative to the thigh assembly around an output shaft of the fourth torso motor within a plane formed by the second direction and a third direction. Two opposite sides of the end of the thoracic cavity assembly facing away from the thigh assembly are provided with the robotic arms respectively, and the gripper structures are securely mounted at tail ends of the robotic arms respectively.

The present invention provides a linear member shape simulator, a method, and a program for a multi-joint robot that can obtain the shape of a linear member by an approximate curve even for a more complex shape. The linear member shape simulator (D) of the multi-joint robot according to the present invention inputs the positions of one or more passing points between the starting position and the ending position of the linear member, the initial positions of adjustment passing points for adjusting the length of the linear member, and adjustment parameters for the input adjustment passing points, uses the positions of the input passing points, and uses the initial positions of the input adjustment passing points as initial values, and repeatedly executes a shape process for obtaining the shape of the linear member and a length process for obtaining the length of the linear member under the obtained shape of the linear member until the difference between the actual length of the linear member and the obtained length of the linear member becomes equal to or less than an allowable value. Here, the adjustment parameters are changed when the shape process is executed.

To appropriately calculate combinations of angles of respective joints when controlling an articulated robot in which links are connected via multiple joints.SOLUTION: An articulated robot control method performs: target input processing that receives input values such as target coordinates and orientation of a tip apparatus; seed storage processing that stores seeds, which are combinations of angles being references of multiple joints; and inverse motion computing processing that, on the basis of the input values specified by the target input processing, finds combinations of angles of the multiple joints that achieve the target coordinates and orientation of the tip apparatus by solving an inverse motion equation. Therein, the method prepares, as the seeds to be stored by the seed storage processing, all possible combinations of angles obtained by sparsely dividing a movable range of each of the multiple joints, and, in the inverse motion computing processing, obtains the solution of the inverse motion equation for each seed, and obtains the solution close to the seed that achieves the target.SELECTED DRAWING: Figure 1

The multi-joint robot with the multiple degrees of freedom relates to the technical field of intelligent manufacturing equipment, and comprises a lower shell, an upper shell is arranged on the top of the lower shell, and a multi-joint mechanism is arranged on the upper shell; the multi-joint mechanism is composed of a six-axis mechanical arm fixed to the center of the top of the upper shell and an inner driving motor fixed to the bottom of the six-axis mechanical arm, the inner driving motor is located in the upper shell, and self-tensioning crawler belt mechanisms are symmetrically arranged on the two sides of the lower shell. The output shaft drives the rotating disc and the driving frame to move, rotary motion is converted into reciprocating swing of the swing frame, then the mounting frame and the supporting roller are driven to do synchronous reciprocating motion, the supporting roller pulls the connecting belt to move, and the cleaning brushes evenly arranged on the connecting belt synchronously act along with the connecting belt and are tightly attached to the surface and gaps of a walking crawler belt. Through brushing, sweeping and scraping actions, impurities such as metal chippings and cutting dust attached to the gaps of the crawler belts are effectively stripped, and dynamic brushing of the gaps of the crawler belts in the walking process is achieved.

1. Name of the designed product: mechanical arm (multi-joint for dangerous object disposal robot) 2. Use of the designed product: mechanical arm for grabbing dangerous objects for disposal 3. Design points of the designed product: in shape 4. Picture or photo best indicating the design points: perspective view 1

The invention belongs to the technical field of industrial robot mechanical arm control, and provides a stability control method and system for a multi-joint mechanical arm of a sand blasting robot, and the method comprises the steps: obtaining a dynamic model of the multi-joint mechanical arm of the sand blasting robot; adopting a time-varying convergence function of a stable preset finite time control strategy to perform state transformation on the obtained dynamic model to obtain a virtual control signal and an actual control input signal of the dynamic model; and the stability of the dynamic model is analyzed based on the obtained virtual control signal and the actual control input signal, a stable point of the dynamic model is determined, the actual torque of the mechanical arm is controlled to be kept continuous on the two sides of the determined stable point correspondingly, and stability control over the multi-joint mechanical arm of the sand blasting robot is completed according to the actual torque of the mechanical arm.

This invention discloses a fault diagnosis method for hydraulically driven multi-joint robot systems, belonging to the field of multi-joint robot fault diagnosis technology. It aims to solve the problems of easy misjudgment based on single parameters, difficulty in tracing the source of anomalies in related parts, and difficulty in adapting to complex environments and multi-stage operations. The method includes: dividing the operation into stages, identifying key parts, collecting operational and environmental parameters and storing them according to association patterns to establish a dynamic association library; dividing environmental intervals, combining the operation stages and environmental intervals to construct a model containing single parameters and collaborative benchmarks, and matching the model through environmental anomaly diagnosis; comparing the current parameters with the model, diagnosing and locating abnormal components, and analyzing the proportion of abnormal parameters, correlation coefficients, and degree of collaborative deviation to determine potential faults; if a fault exists, establishing an association graph and fault influence chain to identify the source of the anomaly. This achieves multi-dimensional accurate diagnosis, reduces misjudgments, efficiently traces the source of anomalies, and improves the adaptability of fault diagnosis in complex environments and multi-stage operations.

The invention discloses a posture control method and system of a discrete gravity center double-wheel-foot robot and a storage medium, and relates to the technical field of gravity center control. Discrete configuration and rapid switching of the gravity center position are achieved by actively adjusting hip joints and knee joints, and a robot model is established based on multi-rigid-body dynamics; simplifying the model into an inverted pendulum linear model family with parameters changing along with the gravity center in the front-back direction; a plurality of discrete gravity center working conditions are preset, each working condition corresponds to a specific joint target angle and model parameters, and the optimal working condition is selected for switching according to the real-time posture and the motion state; and designing a cooperative control law by adopting a linear quadratic regulator, and finally, realizing stable attitude control of the robot under complex terrains and disturbances through multi-joint cooperative execution. According to the method, the disturbance rejection capability and the attitude stability margin are remarkably improved through discrete gravity center configuration, meanwhile, the model complexity and the real-time calculation burden of continuous gravity center adjustment are avoided, and control performance and engineering realizability are achieved at the same time.

The wheel-foot conversion multi-legged robot comprises a body, the side surface of the body is provided with a plurality of driving parts distributed in the circumferential direction, a multi-joint leg, the proximal end of the multi-joint leg is hinged to the driving part, the multi-joint leg comprises a plurality of joint arms arranged in a straight line and hinged in sequence, wherein the two ends of the joint arm farthest from the proximal end are respectively provided with a walking wheel and a gripping foot, both can support and drive the wheel-foot conversion multi-legged robot, and the robot realizes wheel running and foot running mode conversion by switching the use of the walking wheel and the gripping foot of the multi-joint leg. The multi-legged robot designed by the utility model can be switched between the use of the walking wheel and the gripping foot, and then the wheel running and foot running mode conversion is realized, and the innovative design significantly enhances the obstacle crossing ability of the robot.

The invention relates to a detection system. The detection system includes a robot arm, a laser sensor, and a control device. The robot arm includes a base, a multi-joint arm connected to the base, and a capacitance-type proximity sensor provided on the multi-joint arm and detecting an interfering object. The laser sensors are provided at positions facing each other with respect to the base, and emit laser light in a direction substantially parallel to a mounting surface of the robot arm to detect an interfering object. The control device stops or decelerates the operation of the robot arm on the basis of the detection result of the interfering object obtained by at least one of the capacitive proximity sensor and the laser sensor. The beneficial effect is that the interference object approaching the mechanical arm can be detected in a high-precision and large-range manner.