Abstract: 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.

Abstract: A motion planner of an autonomous vehicle's computer system uses reconfigurable collision detection architecture hardware to perform a collision assessment on a planning graph for the vehicle prior to execution of a motion plan. For edges on the planning graph, which represent transitions in states of the vehicle, the system sets a probability of collision with a dynamic object in the environment based at least in part on the collision assessment. Depending on whether the goal of the vehicle is to avoid or collide with a particular dynamic object in the environment, the system then performs an optimization to identify a path in the resulting planning graph with either a relatively high or relatively low potential of a collision with the particular dynamic object. The system then causes the actuator system of the vehicle to implement a motion plan with the applicable identified path based at least in part on the optimization.

Abstract: A system for motion planning for autonomous vehicles can include a plurality of sensors, a plurality of detectors in electrical communication with the plurality of sensors, and a motion planning module in electrical communication with the plurality of detectors and a computing system of an autonomous vehicle. The motion planning module stores a planning graph with each node representing, explicitly or implicitly, time and variables defining a state of the autonomous vehicle, an operating environment, or both the state of the autonomous vehicle and the operating environment. A reconfigurable processor can include a collision detection module and, optionally, a shortest path module. Pre-computed collision data and planning graph data reflecting logical/physical node mapping can be communicated to the processor during a programming phase and used during runtime.