The present teaching relates to a method and system for path planning. A target is tracked via one or more sensors. Information of a desired pose of an end-effector with respect to the target and a current pose of the end-effector is obtained. Also, a minimum distance permitted between an arm including the end-effector and each of at least one obstacle identified between the current pose of the end-effector and the target is obtained. A weighting factor previously learned is retrieved and a cost based on a cost function is computed in accordance with a weighted smallest distance between the arm including the end-effector and the at least one obstacle, wherein the smallest distance is weighted by the weighting factor. A trajectory is computed from the current pose to the desired pose by minimizing the cost function.

A robotic system to facilitate simultaneous human laborer and robotic tasks on an article. The system includes data acquisition from a non-point cloud camera and implementation by a mid-tier consumer grade workstation. Nevertheless, a motion plan may be carried out by the robotic aid in a manner that allows for on-the-fly adjustment to a second motion plan to avoid collision with the laborer during the performed tasks.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for converting between different representations of collision exclusion relationships. One of the methods includes identifying a plurality of cliques in a collision exclusion graph. A bitmask representing collision exclusion relationships between the particular object and other objects in the robotic operating environment is generated using the identified cliques. A simulation of executing a robotic control plan for a robot in the robotic operating environment is performed using the generated bitmasks to detect collisions.

A robotic arm obstacle avoiding path planning method is provided. The method includes the following steps: step 1: simplifying the robotic arm model and obstacles, determining robotic arm joint points, and adopting virtual joint interpolation to interpolate connecting rods between adjacent joints; employing spherical bounding boxes at each joint point to envelop and replace the robotic arm model, enabling complete substitution for distance calculation when the robotic arm assumes any posture; step 2: adopting an eye-to-hand configuration to position the depth camera, acquiring in real time the point cloud information of the robotic arm and obstacles in the workspace, and using a robot real-time filtering package to filter out the point cloud information of the robotic arm itself.

A robotic arm obstacle avoiding path planning method is provided. The method includes the following steps: step 1: simplifying the robotic arm model and obstacles, determining robotic arm joint points, and adopting virtual joint interpolation to interpolate connecting rods between adjacent joints; employing spherical bounding boxes at each joint point to envelop and replace the robotic arm model, enabling complete substitution for distance calculation when the robotic arm assumes any posture; step 2: adopting an eye-to-hand configuration to position the depth camera, acquiring in real time the point cloud information of the robotic arm and obstacles in the workspace, and using a robot real-time filtering package to filter out the point cloud information of the robotic arm itself.

Solutions for multi-robot configurations are co-optimized for wear, collision and optionally for performance and/or energy expenditure, across a set of non-homogenous parameters based on a set of tasks to be performed by a set of robots. Non-homogenous parameters may include two or more of: the respective base position and orientation of the robots, an allocation of tasks to respective robots, respective target sequences and/or trajectories for the robots. Such may be executed pre-runtime. Output may include for each robot: workcell layout, an ordered list or vector of targets, optionally dwell time durations at respective targets, and paths or trajectories between each pair of consecutive targets. Output may provide a complete, executable, solution to the problem, which in the absence of variability in timing, can be used to control the robots without any modification. A genetic algorithm, e.g., Differential Evolution, may optionally be used in generating a population of candidate solutions.