Framework of robotic online motion planning

A method for motion planning of an industrial robot, said method comprising:

• computing and selecting a planned path comprising a set of waypoints based on input information including a start point and a goal point for the planned path and data defining obstacles to be avoided, by a computer having a processor and memory, including computing and selecting the planned path using either a parallel combination or a serial combination of a sampling-based collision-free motion planning method and an optimization-based collision-free motion planning method, where the optimization-based collision-free motion planning method determines the waypoints in the planned path by iteratively computing the waypoints from the start point to the goal point using an objective function for path quality and a constraint function for collision avoidance;
• computing a reduced set of command points representing the planned path, by the computer, where a number of waypoints in the planned path is greater than a number of command points, where computing the reduced set of command points includes computing a spline curve function to fit the waypoints of the planned path, where an arc length parameter having a value in a range of zero to one defines a position on the spline curve function, and evaluating the spline curve function at each of the command points based on the arc length parameter and the number of command points;
• transferring the reduced set of command points to a robot controller;
• and
• computing robot joint motions to cause a tool on the robot to follow the planned path, by the robot controller, based on the command points.

A path planning system for an industrial robot, said system comprising:

• means for providing input information depicting a workspace, including a start point and a goal point for a path of a tool, and data defining obstacles to be avoided;
• a computer in communication with the means for providing input information, said computer having a processor and memory configured for computing and selecting a planned path comprising a set of waypoints based on the input information, including using a combination of a sampling-based collision-free motion planning method and an optimization-based collision-free motion planning method, where the optimization-based collision-free motion planning method determines the waypoints in the planned path by iteratively computing the waypoints from the start point to the goal point using an objective function for path quality and a constraint function for collision avoidance, and computing a reduced set of command points representing the planned path, where a number of waypoints in the planned path is greater than a number of command points, where computing a reduced set of command points includes computing a spline curve function to fit the waypoints of the planned path, where an arc length parameter having a value in a range of zero to one defines a position on the spline curve function, and evaluating the spline function at each of the command points based on the arc length parameter and the number of command points;
• and
• a robot controller in communication with the computer and the robot, said controller being configured for computing robot joint motions to cause the tool on the robot to follow the planned path based on the reduced set of command points received from the computer.