Robot joint space graph path planning and move execution

A method comprising:

• determining, by a processing device and within a joint space of a robot arm, a start point and an end point of one or more end effector for a complete movement of the robot arm to transfer a substrate positioned on the one or more end effector, the robot arm comprising multiple joints and the end effector;
• identifying, by the processing device from a grid of joint positions within joint ranges of the multiple joints and using a first granularity, a plurality of reachable positions by the multiple joints and the one or more end effector, the grid being within the joint space and including the start point and the end point;
• building, by the processing device, a graph that includes nodes to represent the plurality of reachable positions that also satisfy Cartesian limits of the robot arm within the joint space based on joint position combinations for respective ones of the plurality of reachable positions;
• adding, by the processing device to the graph, edges that interpolate between nearest neighbor nodes of the nodes that complete multiple paths between the start point and the end point, wherein the edges also satisfy the Cartesian limits;
• calculating, by the processing device, distances of the edges of the graph;
• and
• executing, by the processing device, a graph optimization algorithm on the graph to determine one of multiple shortest paths or lowest cost paths through the nodes between the start point and the end point.

A non-transitory computer-readable medium storing instructions, which when executed by a processing device, cause the processing device to execute a plurality of operations comprising:

• determining, within a joint space of a robot arm, a start point and an end point of one or more end effector for a complete movement of the robot arm to transfer a substrate positioned on the one or more end effector, wherein the robot arm comprises multiple joints and the one or more end effector;
• building, with respect to the joint space for the multiple joints and the one or more end effector, a graph of reachable positions and sub-paths between the reachable positions, wherein the reachable positions and the sub-paths satisfy Cartesian limits within the joint space, and the reachable positions are identified at a granularity that divides the complete movement into multiple sub-movements of the robot arm;
• determining, by executing a graph optimization algorithm on the graph, multiple paths, each made up of a group of the sub-paths, that have one of shortest distances or lowest costs between the start point and the end point;
• and
• selecting a path, of the multiple paths, through the graph that minimizes move time of the one or more end effector between the start point and the end point while satisfying torque limits on the multiple joints and an acceleration limit on the end effector.