Realtime Robotics, Inc.

Sean Murray

William Floyd-Jones

George Konidaris

Daniel Sorin

Xianchao Long

Peter Howard

Luca Colasanto

Matthew Ryan

Arne Sieverling

Collision detection useful in motion planning for robotics advantageously represents planned motions of each of a plurality of robots as obstacles when performing motion planning for any given robot in the plurality of robots that operate in a shared workspace, including taking into account the planned motions during collision assessment. Edges of a motion planning graph are assigned cost values, based at least in part on the collision assessment. Obstacles may be pruned as corresponding motions are completed. Motion planning requests may be queued, and some robots skipped, for example in response to an error or blocked condition.

Motion planning for multiple robots in shared workspace

Collision detection useful in motion planning for robotics advantageously employs data structure representations of robots, persistent obstacles and transient obstacles in an environment in which a robot will operate. Data structures may take the form of hierarchical data structures ((e.g., octrees, sets of volumes or boxes (e.g., a tree of axis-aligned bounding boxes (AABBs), a tree of oriented (not axis-aligned) bounding boxes, or a tree of spheres)) or non-hierarchical data structures (e.g., Euclidean Distance Fields) Such can result in computational efficiency, reduce memory requirements, and lower power consumption. The collision detection can take the form as a standalone function, providing a Boolean result that can be employed in executing any of a variety of different motion planning algorithms.

Collision detection useful in motion planning for robotics

A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change.

Motion planning of a robot storing a discretized environment on one or more processors and improved operation of same

A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change. Various aspects of such robot motion planning are implemented in particular systems and methods that facilitate motion planning of the robot for various environments and tasks.

Motion planning of a robot for various environments and tasks and improved operation of same

A processor-based system provides a user interface to facilitate generation of motion planning graphs or roadmaps, for example via autonomous generate of additional poses, for example neighboring poses, based on specified seed or origin pose, and/or generate or sub-lattice connecting poses and/or edges to couple separate regions or sub-lattices of the motion planning graph together. Such may include performing collision-checking and/or kinematic checking (e.g., taking into account kinematic constraints of robots being modeled). The resulting motion planning graphs or roadmaps are useful in controlling robots during runtime. Robots may include robots with appendages and/or robots in the form of autonomous vehicles.

Motion planning graph generation user interface, systems, methods and articles

Solutions for multi-robot configurations are co-optimized, to at least some degree, across a set of non-homogenous parameters based on a given set of tasks to be performed by robots in a multi-robot operational environment. 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.

Growing community of inventors

Boston, MA, United States of America

Sean Murray