52 results about "Robot learning" patented technology

The invention discloses a robot imitation learning method based on a diffusion model, and belongs to the technical field of robot learning and body intelligence. Comprising the following steps: carrying out standardization processing on input image observation data and a robot state, and carrying out image enhancement by adopting gray scale transformation, random erasure and Gaussian blur; based on the enhanced image and the robot state, training a diffusion model to generate an action sequence, including forward diffusion, conditional feature fusion, noise prediction and joint loss optimization; in real-time control, features are extracted through an image enhancement network, sampling is accelerated through DDIM to generate an action sequence, noise scheduling coefficients are dynamically adjusted based on visual feature differences, and closed-loop optimization is achieved. According to the method, the image enhancement technology and the diffusion strategy are deeply fused, joint optimization of visual features and action sequences is achieved, the action generation accuracy and robustness of the robot under the complex visual interference and small sample conditions are remarkably improved, and the success rate is improved by 18% compared with a base line under 40 sample sizes.

A method may include receiving input data identifying an operation to be completed in an environment. The method may also include identifying, using an artificial intelligence (AI) model, a series of tasks to be performed by robots to complete the operation based on the input data. In addition, the method may include identifying a subset of the robots to perform the series of tasks based on capabilities to be used to perform the series of tasks. Further, the method may include causing the subset of the robots to autonomously perform the series of tasks to complete the operation.

The application provides a method for determining development parameters of a natural gas hydrate reservoir and related equipment. In the process of particle swarm intelligent optimization, a robot learning algorithm is used for data mining and training to obtain a training model. The potential particles are determined based on the training model. The global optimal objective function is determined based on the combination of the potential particles and the updated development parameters. In the case where the convergence condition is reached based on the development parameter combination corresponding to the global optimal objective function value, the development parameter combination corresponding to the global optimal objective function value is determined as the target development parameter combination. The calculation process of the intelligent optimization algorithm can be improved by the machine learning algorithm, and the optimization time of the development parameters of the natural gas hydrate reservoir is shortened.

A data collection system that performs data collection of human-driven robot actions for robot learning. The data collection system includes: i) a wearable computation subsystem that is worn by a human data collector and that controls the data collection process and ii) a human-machine operation interface subsystem that allows the human data collector to use the human-machine operation interface to operate an attached robotic gripper to perform one or more actions. A user interface subsystem receives instructions from the wearable computation subsystem that direct the human data collector to perform the one or more actions using the human-machine operation interface subsystem. A visual sensing subsystem includes one or more cameras that collect raw visual data related to the pose and movement of the robotic gripper while performing the one or more actions. A data collection subsystem receives collected data related to the one or more actions.

The application discloses a kind of robot learning methods, equipment and medium based on blockchain, method includes: determining the blockchain platform created based on blockchain framework in advance;Determine operation instruction, and write operation instruction in blockchain platform;Receive the operation request sent by robot;According to operation request, and the operation instruction stored in blockchain platform, determine the current operation instruction corresponding to the robot;Send current operation instruction to robot, to make robot execute corresponding operation mode based on current operation instruction.The whole process of robot learning and obtaining operation instruction is stored in blockchain platform.As blockchain platform is distributed storage, data tampering of single node will not take effect, which ensures the authenticity and credibility of data on the blockchain platform.When robot encounters new working scenario, it only needs to obtain corresponding operation instruction in blockchain platform to work, without artificial re-editing, which improves work efficiency.

The present application relates to a kind of soft landing reward function-based quadruped robot low-noise gait control method and system, the method includes: constructing quadruped robot motion control environment, and defining foot contact determination standard;Design soft landing reward function based on vertical contact force, for the negative punishment of large contact force at the moment of landing, guide quadruped robot to learn low contact force landing mode;Collect the real-time contact force of quadruped robot foot and historical contact state, with soft landing reward function as core optimization target, using reinforcement learning algorithm, in combination with gait stability constraint, iterative training is carried out to strategy network, and low-noise gait strategy network is obtained, for optimizing output gait control signal, to control the gait action of quadruped robot accordingly.Compared with prior art, the present application can consider the noise control and gait stability of robot by accurately determining the moment of landing, designing contact force negative reward and combining reinforcement learning to actively optimize gait strategy.

The invention relates to a robot, a learning data collection device, a learning data collection method, and a computer program product. A robot capable of collecting learning data for recognizing a speaker from speech includes: an external stimulus detection unit that detects an external stimulus; a data collection unit that, when the external stimulus detection unit detects, as the external stimulus, speech data indicating the detected speech, as the learning data, stores the speech data in a storage unit, in a case where the speech satisfying a given collection condition is detected by the external stimulus detection unit as the external stimulus; and a condition changing unit that, when the external stimulus detection unit detects the external stimulus that satisfies a specific condition, changes the collection condition for a period from the detection of the external stimulus that satisfies the specific condition until a prescribed time elapses, and changes the collection condition for a period from the detection of the external stimulus that satisfies the specific condition to the detection of the external stimulus that satisfies the specific condition. The external stimulus detection unit is configured to detect the external stimulus such that the speech detected by the external stimulus detection unit is easy to satisfy the collection condition.

The application belongs to the technical field of intelligent control of legged robots, and particularly relates to a legged robot reinforcement learning control method based on a constrained Markov decision process and manifold variance compression, which comprises collecting multi-source state data of the legged robot and preprocessing the same; constructing a strategy-value network and a danger assessment network; proposing state-dependent manifold variance compression and performing action sampling; constructing a Lagrange model of the constrained Markov decision process; updating the strategy network and performing alternating optimization of the Lagrange multiplier. The application can adaptively compress the exploration noise of high-risk joints in the strategy training process, and simultaneously realize automatic balancing of multiple physical constraints through a dynamic Lagrange multiplier, so as to fundamentally improve the running safety and robustness of the legged robot under extreme postures and complex working conditions while ensuring the learning efficiency of the legged robot, and provide reliable protection for real physical deployment.

Robot teaching device (10) for generating an operating program (16) for a robot (20) by arranging command symbols (60 to 64) expressing operating commands for the robot (20), comprising a marker indicator (43) which, when an operating command contains multiple position data, displays multiple markers (69) relating to identifiers (68) of the position data in conjunction with a single command symbol (61) on it.

The embodiment of the application provides a robot precise landing planning method and device based on a priori terrain model, which carries out digital modeling on a preset terrain in a simulation environment, constructs a digital map containing terrain geometry and semantic information, and clearly calibrates the center coordinates of each ideal landing area as a target landing point. In the training process, the global coordinates of the robot foot end are tracked in real time, and the three-dimensional deviation of the robot foot end from the nearest target landing point is determined through map mapping, and then a reward function with the deviation size as the evaluation index is designed to drive the robot to learn a high-precision landing strategy. The present application introduces the priori terrain target point as a guide, so that the reward signal has a clear geometric meaning and can directly and efficiently drive the strategy to converge to the precise landing behavior, greatly improving the motion accuracy and reliability on the structured terrain.

The application relates to an artificial intelligence technology, which can be applied to a medical health, financial technology and other business system platform, and discloses a robot control method, device, equipment and medium based on artificial intelligence, which comprises the following steps: decomposing a natural language task instruction; generating a planning path instruction of a robot according to the decomposed task; executing the planning path instruction in a simulation environment, and outputting operation track information of the robot and environment state change data; verifying the simulation execution result, and if the verification is successful, storing the natural language task instruction, the decomposed task, the operation track information and a success label as multi-modal information; training an initial diffusion strategy model based on the multi-modal information, generating a robot decision model; and controlling the robot based on the robot decision model. The application significantly improves the learning efficiency and robustness of the robot through an automatic and large-scale data generation process, and can respond to natural language instructions to execute multi-task.

This invention discloses a method, system, terminal, and medium for generating embodied intelligence training corpus based on adversarial data governance, relating to the field of robot learning technology. The key technical points are: acquiring multimodal data streams generated by robots during human-machine collaborative interaction; performing time alignment processing on the multimodal data streams to obtain aligned standardized data streams; identifying high-value data segments from the standardized data streams using a preset value evaluation function; and performing coordinate regularization processing on the identified high-value data segments to generate training corpus. This invention introduces an adversarial operator role into the human-machine collaborative loop, systematically injecting multidimensional perturbations and actively generating high-difficulty edge scenario data containing instability-recovery logic. This results in training corpus that not only has extremely high information density, covering failure-recovery manifolds that are difficult to collect using traditional data, but also possesses strong generalization characteristics.

A robotic device includes a robot having an end-effector, and a large modality model (LMM) pre-trained on vision-language tasks and fine-tuned on image-visual trace pairs. A method of predicting a next sequence of actions for a robot using a large modality model (LMM) includes receiving, at the LMM, an image input and a language input, using the LMM to predict a next action sequence for a robot having an end-effector, and using the LMM to produce predicted visual traces of the end-effector.

Implementations are provided for an interactive machine learning methodology that allows non-expert users to use natural language to teach new skills, particularly to robots, through language grounding and understanding. In various implementations, a plurality of natural language summaries may be retrieved. Each of the natural language summaries may describe details of robotic performance of a task, and may include, or be usable to retrieve, a corresponding set of reference modulation values. A set of modulation values corresponding to a natural language request may be generated based on the plurality of natural language summaries. The natural language request may specify one or more constraints on robotic performance of the task. A robot control signal may be generated based on the generated set of modulation values.

A robot training apparatus according to an embodiment may perform the operations of: acquiring state information including a state of a pallet and the size of an object to be loaded onto the pallet; converting the state information into a patch of a predefined size in order to input same into a vision transformer model; on the basis of an actor network of a reinforcement learning model including a policy function for determining a loading position of the object in the direction that maximizes an expected value of the final loading rate of the pallet, determining, from the patch, a position to load the object onto the pallet; on the basis of a critic network of the reinforcement learning model including a value function for deriving the expected value according to the determination, deriving an expected value according to the determination; and updating parameters of the policy function and the value function in the direction that minimizes a loss of a loss function calculated on the basis of the determination and the expected value.

Systems, apparatus, and methods are described for robotic learning, planning, and execution of skills, including navigation using elevators. In one or more embodiments, a robotic device may need to autonomously take an elevator, e.g., by using its autonomy features and / or relating on application programming interfaces (APIs) to communicate with elevators.

This utility model discloses a laser marking data acquisition device, including a support, a laser, a gripper, and an information collector. The laser, mounted on the support, emits laser light towards a target object to form a positioning mark on the target object. The gripper, mounted on the support, grips the target object. The information collector, mounted on the support, collects image and / or voice information when the gripper grips the target object. This laser marking data acquisition device, by using a laser to emit laser light and form positioning marks on a target object, can significantly identify the target object, thereby improving the positioning accuracy. When a robot learns the semantic data with positioning marks collected by this utility model, it helps the robot better understand semantic information in the environment, significantly improving the robot's operational capabilities and intelligence level.

The application discloses a kind of service robot artificial marking data screening methods for old users, belong to intelligent robot technical field.Service robot when entering certain old user home environment, according to new category data collected in user home environment, need select the image most easily to old user labeling with most learning value, present it to user for labeling.The specific screening method is: robot is with three kinds of attributes (perception brightness, contrast, size) of image as feature, in combination with image labeling difficulty prediction model, obtain the labeling difficulty prediction of image for old user.Combining the labeling difficulty prediction value of image with other three kinds of index describing image learning value, calculate the screening value measure of image, and then according to the measure select a certain proportion of value measure maximum image, as request old user to give out labeling and require robot learning data.

The application discloses an AI robot self-training system based on a traditional opera action library, and aims to solve many problems existing in traditional opera inheritance and teaching. The system mainly comprises a traditional opera action library construction module, an AI robot learning module and a self-training optimization module. By using deep learning and reinforcement learning algorithms, the AI robot can autonomously learn and optimize actions, greatly improving the learning efficiency. Compared with traditional traditional opera teaching methods, the AI robot can tirelessly learn and train, and can master a large number of traditional opera actions in a short time. The system can also be applied to the traditional opera training market, provide a new teaching tool for training institutions, reduce training costs and improve training quality.

One or more embodiments of the present disclosure may include a method. The method may include receiving an instruction identifying an operation to be completed by a robot. The method may also include identifying, using an artificial intelligence (AI) model, a task to be performed by the robot to complete the operation. Additionally, the method may include identifying, using the AI model, a series of movements to be made by the robot to perform the task. Further, the method may include identifying, using the AI model, a series of raw electrical signals configured to cause actuators to move the robot in accordance with the series of movements. The method may include generating the series of raw electrical signals to cause the actuators to move the robot in accordance with the series of movements and cause the robot to perform the task.

The application discloses a scenario memory-based robot training system and method in the technical field of artificial intelligence and robot learning, and solves problems of lack of effective memory scheduling system, non-intelligent experience value quantization mechanism and insufficient multi-modal information fusion capability in existing robot training methods.The system comprises a perception module, a multi-modal unified memory encoder, a progressive memory scheduling system, a multi-dimensional value quantization evaluation mechanism, an intelligent experience hierarchical scheduler, a multi-modal unified encoding retriever, a strategy generation module, an execution module and an anomaly detection module.The multi-modal unified memory encoder adopts a hierarchical dimension reduction Transformer architecture, and fuses an RGB image, a depth image, force sensor data and joint angle information into a 576-dimensional unified feature vector.The progressive memory scheduling system comprises a working memory, a short-term memory and a long-term memory three-layer structure.The multi-dimensional value quantization evaluation mechanism quantitatively scores experience based on reward evaluation, novelty evaluation and uncertainty evaluation.

Embodiments of the present application provide a robot moving path adjustment method based on robot learning and related devices, which are applied to a robot in an intelligent warehousing system, the intelligent warehousing system comprising the robot and a scheduling device; the method comprises: obtaining moving information sent by the scheduling device, the moving information comprising a first physical space position navigation coordinate in a warehouse space for indicating; moving in the warehouse space according to the moving information; when moving to a second physical space position according to the moving information, determining whether there is historical deviation information corresponding to the navigation coordinate; if there is historical deviation information, performing position adjustment processing according to the historical deviation information to correct the first deviation value; if there is no historical deviation information, obtaining position information of a current position to perform position adjustment processing. In this way, the deviation between the expected position and the actual position is reduced, and the walking accuracy of the robot is improved.

The invention relates to a quadruped robot low-noise gait control method and system based on a soft landing reward function, and the method comprises the steps: constructing a quadruped robot motion control environment, and defining a foot contact judgment standard; a soft landing reward function based on vertical contact force is designed and used for conducting negative punishment on large contact force at the landing moment, and the quadruped robot is guided to learn a low-contact-force landing mode; real-time contact force and historical contact states of feet of the quadruped robot are collected, a soft landing reward function is used as a core optimization target, a reinforcement learning algorithm is adopted, gait stability constraints are combined, iterative training is conducted on a strategy network, and a low-noise gait strategy network is obtained and used for optimizing and outputting gait control signals. Therefore, the gait action of the quadruped robot is correspondingly controlled. Compared with the prior art, noise control and gait stability of the robot can be considered by accurately judging the landing moment, designing the contact force negative reward and combining the reinforcement learning active optimization gait strategy.

The application discloses a data enhancement method based on humanoid robot reinforcement learning, comprising the following steps: step S1: parallel training environment building; step S2: parallel training; step S3: training data acquisition; step S4: data enhancement; step S5: training task loss calculation; and step S6: strategy updating. The application proposes a data enhancement method based on humanoid robot reinforcement learning, which can significantly improve the speed of reinforcement learning training, reduce the training data required by the robot in reinforcement learning by using the data enhancement method, enhance the left-right symmetry of the robot behavior, improve the aesthetic of the action, and the proposed data enhancement method can also be applied to other robot learning methods such as imitation learning.

A robot learning method for performing a learning process to generate robot motion data based on a measurement of a work movement that involves actuation on an actuation object (7, 8) by a hand (5) of a teacher (U1), wherein the robot motion data include a sequence of joint displacement as a movement of a robot hand mechanism (6) corresponding to the working movement, wherein The robot learning process, as steps performed by a computer system (100), includes the following: a step of capturing a first measured posture, which is obtained by measuring a time series posture that includes a position and posture of the actuated object (7, 8) during the work movement; a step of capturing a second measured posture, which is obtained by measuring a time series posture, which includes a position and posture of the hand (5) of the teacher (U1) during the work movement; a step of the teacher's (U1) recording the activity on the object of activity (7, 8); and a step of generating a learning posture to generate the robot motion data based on the first measured posture, the second measured posture and the recorded activity.

A robot learning dataset construction method, a humanoid robot, and a computer-readable storage medium are provided. The method includes: a robot operator uses an inertial motion capturing device to remotely operate a humanoid robot to perform various operation tasks, construct a dataset by collecting real-time working images and real-time joint motion data of the humanoid robot performing various operation tasks under manual guidance, thereby utilizing the flexible combination of the human body posture direct extraction characteristics of the inertial motion capturing device and the flexibility and reliability of executing robot remote operation tasks so as to improve the construction efficiency, dataset validity, and dataset integrity of the task learning dataset, which facilitates further improvement of the generalization and accuracy of the imitation learning of the humanoid robot.

A brain-like decision-making and motion control system is disclosed, this system comprises an active decision-making module, an automatic decision-making module, an evaluation module, a memory module, a perceptual module, a compound control module, an input channel module, an output channel module, and a controlled object module. The three working modes supported by the system include an active supervision mode, an automatic mode, and a feedback-driven mode, which enables the robot to make autonomous decisions to select targets and operations and delicately control actions in the process of interacting with the environment, and can make the robot learn new operations by trial and error, imitation, demonstration, with the flexibility to adapt to the complex task and the environment.

The invention discloses a data enhancement method based on humanoid robot reinforcement learning. The method comprises the following steps: S1, building a parallel training environment; s2, parallel training is carried out; s3, acquiring training data; s4, data enhancement; s5, calculating the loss of the training task; and S6, updating the strategy. The invention provides a data enhancement method for reinforcement learning of a humanoid robot, and the method can remarkably improve the speed of reinforcement learning training, can reduce the training data needed by the robot in reinforcement learning, can enhance the left-right symmetry of robot behaviors, improves the beauty of actions, and improves the training efficiency. The proposed data enhancement method can also be applied to other robot learning methods such as imitation learning.