362 results about "Motion planning" patented technology

The invention provides a cleaning robot multi-mode motion control system, method and equipment and a medium, and belongs to the technical field of intelligent robot control. The system comprises a multi-modal data acquisition module used for performing multi-source synchronous acquisition on an environment image, distance information, a voice signal and a collision signal and outputting original sensing data; the data fusion and processing module is used for receiving the original sensing data, sequentially executing space-time alignment correction, multi-source feature fusion and instruction semantic analysis, and outputting an environment sensing result and a structured control instruction; the motion planning and decision-making module is used for executing global path planning, dynamic obstacle trajectory prediction and motion parameter decision-making based on the environment perception result and the structured control instruction, and outputting a motion control instruction containing a motion mode, a speed and an angle; and the motion control execution module is used for receiving the motion control instruction, converting the motion control instruction into an execution mechanism driving signal, realizing closed-loop control through real-time state feedback and outputting a motion execution result.

The invention discloses an obstacle avoidance motion planning method and system for redundant drive of an intelligent process of a welding robot and computer equipment. According to the method, firstly, a motion path of a robot is planned based on welding process redundancy, then a sampling strategy that the position and posture of a welding gun are separated is adopted, then the sampled posture is mapped to a planar two-dimensional space, and the relevance between an obstacle collision boundary and the obstacle avoidance posture of the welding gun is constructed; an incremental extreme gradient lifting model is adopted to carry out probability modeling on the collision boundary and obstacle avoidance attitude relevance, nearest neighbor search and new planning node expansion are carried out based on target cost to obtain new planning nodes, collision detection is carried out on the new planning nodes, and the new planning nodes passing the collision detection are used for incremental learning of an obstacle avoidance model; and finally, an optimization strategy of spherical linear interpolation and cosine slow motion time mapping is adopted to ensure continuity and smoothness of a motion planning path trace. The problem that in the prior art, it is difficult to quickly calculate and generate a collision-free welding track is solved.

Methods for training a series of neural networks to output driving behavior control parameters is disclosed. The training dataset for the neural networks includes sensor-based vehicle driving recordings that may be categorized by geographical area, by qualitative driving behaviors, or by some combination, such that various training data subsets are used to train the series of neural networks. By learning either city-specific driving behavior control parameters, qualitative driving behavior specific driving behavior control parameters, or both, the resulting parameters may then be provided to a motion planning model for use in modeling predictive control for an autonomous vehicle. Rather than relying on XYZ trajectories of agent vehicles when planning future trajectories of the ego vehicle, the motion planning model is adaptive, due to the use of the learned driving behavior control parameters.

The invention provides a mechanical arm control system and control method based on an embedded virtual machine architecture. A real-time operating system and a non-real-time operating system are deployed on the same embedded board card; the non-real-time operating system transmits control words of all the drivers to a driver communication module deployed on the real-time operating system through a control queue based on the received control request, and the driver communication module transmits state data of all the drivers to the non-real-time operating system through a state queue; and the motion planning module deployed on the non-real-time operating system transmits the generated position data to the driver communication module through the position queue according to a preset control period, and issues the control word and the position data to the driver through the driver communication module. By the adoption of the method, the problems that a non-real-time operating system is interrupted, communication stability is poor due to multi-task resource preemption, control response is slow, state coverage is caused by jitter of the non-real-time operating system, and a mechanical arm is stuck due to position transmission jitter can be solved.

The present disclosure provides an example method that includes: (a) obtaining context data descriptive of an environment surrounding an autonomous vehicle, the context data based on map data and perception data; (b) generating, by a proposer and based on the context data: (i) a plurality of candidate trajectories, and (ii) a plurality of actor forecasts for a plurality of actors in the environment; (c) generating, by a ranker and based on the context data, the plurality of candidate trajectories, and the plurality of actor forecasts, a ranking of the plurality of candidate trajectories; and (d) controlling a motion of the autonomous vehicle based on a candidate trajectory selected based on the ranking of the plurality of candidate trajectories, wherein the proposer comprises a first machine-learned model and the ranker comprises a second machine-learned model, and wherein the first machine-learned model and the second machine-learned model use a common backbone architecture.

The invention discloses a water surface unmanned ship path planning method for a narrow water area. The method comprises the following steps: S1, constructing an unmanned ship global-local collaborative path planning model; s2, navigation constraint and uncertain obstacle distribution for narrow water areas such as rivers and lakes are determined, a technical route adopts a'global-local-fusion 'three-layer collaborative framework, and through the method, the feasibility of a global path and the self-adaptability of local obstacle avoidance can be combined, so that the technical route is optimized; the path planning of continuous, safe and efficient motion planning of the unmanned ship in a narrow water area is realized.

The invention discloses an unmanned aerial vehicle motion planning method and system for guiding visual heat conduction based on depth information, and the method comprises the steps: constructing a motion planning model, and inputting a depth image, an unmanned aerial vehicle attitude and an expected speed into the motion planning model, and real-time high-speed obstacle avoidance of the quad-rotor unmanned aerial vehicle in an unknown complex environment is realized. According to the motion planning model, a visual heat conduction module with a global receptive field is adopted as a sensing system trunk, a depth information guide heat conduction operator module is introduced, depth information is coded into an energy weight, and heat conduction calculation is performed after spatial information and scene representation are guided to be coupled, so that the model can focus on a close-range obstacle. The generated depth information guide scene representation is then input to a decision module to generate an action instruction.

The invention relates to the technical field of dexterous hand motion planning, in particular to a dexterous hand motion planning method and system based on deep learning, and the method comprises the steps: obtaining the state information of a dexterous hand, carrying out the multi-modal feature fusion to generate environment perception information, carrying out the dynamic obstacle detection and cooperative signal analysis, generating an obstacle avoidance path, and optimizing the motion path planning. Real-time data are collected through the sensor module, multi-modal features are fused, and environment sensing information is generated to support motion planning of the dexterous hand; collaborative decision-making among multiple dexterous hands is realized by utilizing an internal communication module, and the adaptive ability and task execution efficiency in a complex dynamic environment are remarkably improved. In addition, dynamic obstacle information is shared by prompting a cooperation signal, conflicts are avoided, and the response speed is increased. The method is suitable for efficient motion planning of the dexterous hand in a complex dynamic scene.

The invention discloses a robot fruit grabbing method based on a multi-mode time sequence collaborative prediction algorithm, and aims to solve the problems that the short-time future trajectory is difficult to accurately predict and the grabbing opportunity is difficult to determine due to fruit and branch swinging caused by wind, branch elasticity and platform advancing. According to the method, a multi-modal time sequence is unified through micro-time alignment, uncertainty is quantified, a three-dimensional special Euclidean group and other variable graph converters are constructed, a spiral shaft constraint projection layer is arranged on the edge between the fruit and a fruit stem, and conditional diffusion short-time trajectory prediction of plum algebra parameterization and uncertainty gating triggering are combined; motion planning and closed-loop control of time delay compensation and collision avoidance constraint are executed in a linkage mode, and the technical effects of high-precision short-time three-dimensional pose prediction, grabbing opportunity self-adaptive triggering and high-success-rate stable grabbing are achieved.

The invention discloses a hand-eye cooperative robot control system and method based on dynamic operator arrangement, an upper computer planning layer operates a master control computer to periodically trigger task scheduling, a joint controller of a lower computer execution layer receives an instruction through a redundant bus to perform servo control, hand-eye camera data triggers a visual assembly line through an interrupt event, and a visual assembly line is controlled through a control interface. According to the method, pressure is calculated through visual processing, motion planning and joint control in a load sharing mode, a double-buffering mechanism is adopted to enable current frame visual processing and previous frame motion control to be executed in an overlapping mode, real-time scheduling and parallel computing of tasks are completed, hot data are cached in a memory database, cold data are archived to an HDFS and migrated through an LRU strategy, and the real-time scheduling and parallel computing of the tasks are completed. Data type conversion is automatically derived and performed based on a feature type registry, and conditional branch execution is triggered according to real-time sensor data. According to the control system, cross-hardware plug and play, algorithm flow configurability and data flow real-time sharing are achieved, and the requirement for improving the efficiency of complex operation tasks is met.

The invention belongs to the technical field of robot safety control, and discloses a safe motion planning method for a dual-redundancy mechanical arm. And a linear mapping relation between the joint space speed of the redundant mechanical arm and the speed of an end effector is established. And establishing an end effector speed constraint, a safety distance constraint and a joint amplitude limiting constraint, and fusing a differential kinematics model and the three constraints to establish a multi-target combined constraint model. The optimal decision variable meets the Carlo demand-Kuhn-Tuck condition, the original expression form of the Carlo demand-Kuhn-Tuck condition is defined, and a nonlinear complementary function is introduced to reconstruct the Carlo demand-Kuhn-Tuck condition. Based on an improved Carlo demand-Kuhn-Tuck condition, a vector error function is defined, and an adaptive return-to-zero neural network is designed; and performing iterative solution on the vector error function through an adaptive return-to-zero neural network to obtain an optimal decision variable of the multi-target joint constraint model, taking the optimal decision variable as a mechanical arm joint motion control instruction, and outputting the mechanical arm joint motion control instruction to complete mechanical arm motion planning.

The invention relates to the technical field of intelligent control, and discloses a dexterous hand motion planning and control method based on a visual language motion model, and the method comprises the steps: S1, collecting data, and carrying out the time sequence synchronization and consistency verification of multi-source data; s2, performing dynamic adaptive exponential moving average filtering and calculation processing on the joint sequence, and reconstructing a processing result into adaptive structured features; s3, fusing joint states, inputting the fused joint states into an action head network, splicing online and offline samples into a training batch according to a preset proportion, and determining results to jointly optimize model parameters; s4, performing model reasoning to obtain target action information, performing processing in sequence to generate a smooth low-jitter control sequence, and sending the smooth low-jitter control sequence to the dexterous hand for execution; and S5, the deployment thread issues a control instruction by aligning the annular buffer and the timestamp, triggers a rollback track and allows manual intervention when the control instruction exceeds a threshold value, and writes manual intervention data into an offline buffer. According to the method, efficient, stable and smooth motion control of the dexterous hand can be realized under the condition of extremely few teaching data sets.

Apparatuses, systems, and techniques are described that solve task and motion planning problems. In at least one embodiment, a task and motion planning problem is modeled using a geometric scene graph that records positions and orientations of objects within a playfield, and a symbolic scene graph that represents states of objects within context of a task to be solved. In at least one embodiment, task planning is performed using symbolic scene graph, and motion planning is performed using a geometric scene graph.

The embodiment of the invention discloses a robot autonomous navigation and obstacle avoidance method and system based on multi-sensor fusion. The method comprises the following steps: acquiring multi-dimensional data; fusing multi-dimensional data to generate a robot pose and a local environment point cloud; dividing a front sensing area into a high-reliability green area and a low-reliability red area according to the positions of the red and green light spots, and respectively distributing sensing weights; projecting the local environment point cloud into an occupied grid, performing obstacle detection according to the point cloud density in each grid unit, and multiplying the detection result by the corresponding sensing weight to obtain a sensing energy consumption cost value of the unit; according to the perceived energy consumption cost value, generating a target attraction direction and an obstacle rejection direction on the occupied grid; and generating a motion path based on the attraction direction and the rejection direction, and controlling the robot to advance according to the motion path. According to the invention, deep collaborative optimization of energy consumption cost and motion planning is realized.

The invention discloses a dexterous hand grabbing stability control system and method based on force control compliant interaction.The system comprises a dexterous hand, a mechanical arm, a force sensing module, a touch sensor, an actuator and an upper computer actuator, the dexterous hand is installed at the tail end of the mechanical arm through a mechanical interface, and the dexterous hand and the mechanical arm form a cooperative control closed loop through real-time communication; according to the control mode of the dexterous hand grabbing stability control system, the upper layer completes object positioning and global motion planning through a mechanical arm, the lower layer completes a layered collaborative architecture of contact perception, compliant control and task action execution through a dexterous hand, and compliant grabbing and stable control over objects are achieved. The mechanical characteristics in the grabbing process can be adjusted in a self-adaptive mode, it is ensured that objects with different hardness are stably and smoothly grabbed, and the problem that the objects slide or are damaged is effectively solved.

The invention discloses a robot teaching data generation method based on artificial intelligence, and the method comprises the following steps: randomly extracting one or more objects from a preset 3D object model library containing a large number of diversified objects as an operation target of the cycle when each data generation cycle begins, a robot body is randomly selected from a preset robot model library, and the randomly selected object and the robot are instantiated into a simulation environment. The trajectory generated based on physical simulation and a classical motion planning algorithm naturally meets kinematics and dynamics constraints, is high in data quality, can be directly used for training, provides 3D point cloud and a 2D orthogonal projection drawing, perfectly supports current mainstream robot control models based on 2D vision and 3D point cloud, is completely carried out in a simulation environment, and has a wide application prospect. And equipment loss and potential safety hazards possibly caused by real robot training are avoided.

The invention relates to the technical field of industrial equipment control, and discloses a dynamic maintenance management method and system based on the full life cycle of test equipment, and the method comprises the steps: obtaining a time domain vibration signal and torque current data during the operation of the equipment through a high-frequency vibration sensor and a current loop feedback interface; calculating an accumulated damage gradient parameter representing the physical recession degree of the mechanical transmission chain; the parameters are input into a preset damage stress coupling model to solve the maximum radial impact force allowed to be borne by the damaged part, and the impact force is mapped into a dynamic capability boundary for carrying out logic constraint on the motion planning instruction; and the motion controller reconstructs an ideal speed curve by using the boundary in an interpolation period, and reshapes a torque load spectrum output to a servo motor by reducing the jump of acceleration and deceleration sections. The problem that an existing static control strategy is mismatched with the dynamic aging characteristic of equipment is solved.

A system and method for estimating a collision probability between a robot and a radiance field within a three-dimensional environment includes: determining forward occupancy information indicating potential over-approximating volumes that are able to be occupied by a robot disposed at a starting position; modeling an environment of the robot using a radiance field; and computing a probability of collision between the robot and an obstacle within the environment based on the forward occupancy information and the radiance field. The estimation method is useful for robotic trajectory determination that involves discretizing a trajectory of the robot into a sequence of trajectory segments over time subintervals; computing an upper-bound for a probability of collision between the robot and a radiance field at each of the time subintervals using a Gaussian Splatting model that normalizes 3D Gaussians within the radiance field; and performing real-time trajectory adjustments based on the computed collision probability upper-bounds.

The invention discloses an intelligent interaction robot control system which comprises a sensing input module, a core processing module, an output execution module and a system management and maintenance module. The perception input module collects multi-modal data through a visual, auditory, environment and touch unit; the core processing module carries out fusion analysis on the data and generates a decision instruction through a multi-modal information fusion unit, a situation cognition and decision unit, an emotion calculation unit and a motion planning unit; the output execution module executes an interaction task through a voice unit, an expression action unit and a motion unit; and the system management and maintenance module provides knowledge base, cloud collaboration and energy monitoring support. Through multi-modal information deep fusion and situational cognition, accurate understanding of user intentions and environments is realized, emotional interaction and personalized service capabilities are provided, the problems that an existing system is single in interaction mode and lacks context understanding are solved, and the intelligent level and user experience of the robot are remarkably improved.

The invention discloses a body-equipped robot control system and method based on multi-modal perception and deep learning, and the system comprises a multi-modal perception module which is used for obtaining and fusing visual information, tactile information and proprioceptive information, and generating a unified state representation; the deep reinforcement learning control module adopts a reinforcement learning algorithm based on an actor-commentator framework and is used for representing an output control strategy according to the unified state, and the reinforcement learning algorithm adopts an experience playback mechanism and a target network technology to realize stable learning; the hierarchical motion planning module is connected with the deep reinforcement learning control module and is used for decomposing a complex task corresponding to the control strategy into high-level strategy planning and bottom-level motion execution; the self-adaptive impedance control module is connected with the hierarchical motion planning module and is used for dynamically adjusting impedance parameters of the robot according to interaction information of the robot and the environment; and the safety guarantee module is used for applying constraint optimization to the control strategy or the motion execution so as to ensure the operation safety of the robot.

The invention provides a motion path planning method for a desktop wheeled robot, which comprises the following steps: when a target task is received, loading a behavior tree corresponding to the target task, the behavior tree comprising a tree logic structure composed of a control flow node, a condition node and an action node; periodically executing the behavior tree through a behavior tree engine so as to determine an execution flow according to a logic structure of the behavior tree; when the execution process triggers a specific path planning action node, a task context corresponding to a current task stage is generated, and the task context is multi-dimensional structured data containing target description and planning constraints; dynamically selecting at least one target motion planning algorithm from a plurality of preset motion planning algorithms based on the task context; and generating a current motion path instruction by using the target motion planning algorithm, and controlling the desktop wheeled robot to execute. The method has the technical effect that the planning strategy can be dynamically adjusted according to the task context.

In various examples, policy prediction-based motion planner systems and methods for autonomous and semi-autonomous systems and applications are provided. A scenario tree structure may be generated that represents potential behaviors of one or more peripheral agents based on perception data of a scene within which an ego vehicle operates. A joint MPC algorithm may optimize the motion of an ego vehicle within the context of the scenario tree structure to produce a policy tree structure. An MPC policy prediction model may be trained to predict the policy tree structures that a joint MPC algorithm would produce, given a set of environmental perception data. An ego vehicle may comprise a trained MPC policy prediction model that receives perception data, and based on that input predicts a policy tree structure that may be used to define a motion policy for navigating the ego vehicle through the scene.

The invention provides a control method and device for flexible gait motion planning of a humanoid robot, and the method comprises the steps: in a gait motion period of a target humanoid robot, aiming at each leg part of the target humanoid robot, carrying out the gait motion planning of the target humanoid robot; acquiring preset initial state data and expected state data corresponding to a support phase period of the leg part in the gait motion period; based on the initial state data and the expected state data, respectively determining an amplitude coefficient corresponding to the leg part in the gait motion period and sole landing position data corresponding to the leg part in the support phase period; and based on the amplitude coefficient, determining a foot sole ground contact force value corresponding to each moment of the leg part in the gait motion period, and based on the foot sole landing position data and the foot sole ground contact force value, controlling the target humanoid robot to perform smooth gait motion in the gait motion period. Through the method, the coordination, the stability and the efficiency of the flexible motion planning of the humanoid robot are improved.

A computing system can obtain, through one or more sensor systems onboard an autonomous vehicle, a motion input, a surface element registration input representing one or more tracked surface elements, and a lane alignment input representing one or more lane boundaries. The computing system can provide the motion input, the surface element registration input, and the lane alignment input to a pose estimation system including a localization filter. The pose estimation system can generate one or more pose states of the autonomous vehicle, including a local pose and a global pose. The computing system can determine a motion plan for the autonomous vehicle based on the one or more pose states.

In examples, autonomous vehicles are enabled to negotiate yield scenarios in a safe and predictable manner. In response to detecting a yield scenario, a wait element data structure is generated that encodes geometries of an ego path, a contender path that includes at least one contention point with the ego path, as well as a state of contention associated with the at least on contention point. Geometry of yield scenario context may also be encoded, such as inside ground of an intersection, entry or exit lines, etc. The wait element data structure is passed to a yield planner of the autonomous vehicle. The yield planner determines a yielding behavior for the autonomous vehicle based at least on the wait element data structure. A control system of the autonomous vehicle may operate the autonomous vehicle in accordance with the yield behavior, such that the autonomous vehicle safely negotiates the yield scenario.

The invention discloses a flexible picking motion planning method and system, a product, equipment and a storage medium, belongs to the technical field of mechanical arm humanoid flexible picking, and solves the problems that in the prior art, when single fruits at different positions and postures are picked, flexible track adjustment and posture control picking planning cannot be performed, and the picking efficiency is high. Therefore, the pose requirement in the picking scene conflicts with joint execution, and the adaptability to complex tracks is weak. Collecting demonstration data; constructing a strategy function, inputting a current mechanical arm tail end pose state, obtaining mechanical arm action probability distribution, and generating a current execution action; constructing a multi-dimensional perception neural reward network, and calculating a current total reward; constructing a value function, and obtaining the value advantage of the current execution action in combination with the current total reward; value loss and strategy loss are calculated, and after the strategy function and the value function are updated, the mechanical arm is adopted to execute the current action. The device is used for realizing smooth picking of fresh fruits.

The system can include a motion planner and a vehicle controller. The system can optionally include or operate in conjunction with a remote operator platform, a remote data system (130), and / or any other suitable components. However, the system can additionally or alternatively include any other suitable set of components. The system can function to facilitate causal command of a vehicle based on the vehicle state. Additionally, the system can function to maintain positive train control (PTC) with the distributed command architecture.

The application relates to a motion planning method and device, a robot, a readable storage medium and a program product. A chassis corresponding kinematic model is generated based on chassis state information and each virtual wheel information corresponding to each wheel group, and the speed and angle of each virtual wheel are not related; motion constraint information of the chassis is obtained, and the chassis is subjected to motion planning according to the kinematic model and the motion constraint information. Compared with the traditional motion planning in the switching mode of double Ackerman steering mode and skew mode, the scheme removes the restriction that each wheel in the chassis must rotate at the same angle size and in the opposite direction, constructs multiple virtual wheel information, generates a kinematic model in combination with the chassis state information and the virtual wheel information, and subjects the chassis to motion planning in combination with the kinematic model and the motion constraint information of the chassis, thereby improving the operation efficiency of the chassis.

An apparatus, comprising a memory, configured to store a first data set, comprising kinodynamic data representing a plurality of human-directed movements of a robot; and a second data set, comprising linguistic descriptors of the plurality of human-directed movement of the robot; and a processor, configured to generate a third data set based on the first data set and the second data set, wherein the third data set comprises a plurality of motion primitives of the robot.

The application relates to the technical field of motion planning, and discloses a corner fairing method of an asymmetric Airthoid-arc, which comprises the following steps: constructing a tool path fairing curve which is sequentially connected by a first Airthoid curve, an arc and a second Airthoid curve, and is used for fairing a corner formed by adjacent straight line segments; preliminarily setting a first transition length and a second transition length according to the lengths of the line segments on the two sides of the corner; solving the first and second tangent angles according to geometric constraints, tangential continuity, curvature continuity constraints and position continuity constraints; if there is a solution, analytically calculating a current approximate error; and finally analytically calculating the curvature extreme value and the arc length of the fairing curve. The asymmetric curve structure is adopted, the corner space is fully excavated, the curvature extreme value is small, the arc length can be analytically expressed, and the profile error is controllable, so that the numerical control machining efficiency is improved.