Robot Motion Planning With Sparse Commands and Path Refinement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic motion planning techniques fail to provide high-quality path plans in real-time while utilizing the inherent motion computing capabilities of the robot controller, leading to inefficient communication bandwidth and suboptimal path quality due to reliance on external computers for computation.
Innovation Solution
A robot motion planning technique that uses a combination of sampling-based and optimization-based algorithms on an external computer to plan robot motion, converting dense planned waypoints to sparse command points for the robot controller to compute kinematics and interpolation points, thereby leveraging the controller's capabilities for smooth and efficient motion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If motion planning calculations are performed on an external computer separate from the robot controller, then computation flexibility and algorithm complexity are improved, but communication bandwidth demands increase and robot controller capabilities are underutilized
Solution Approach 1:
The patent divides the motion planning computation into two segments: dense waypoint generation performed on the external computer using sampling-based algorithms, and sparse command point generation performed on the robot controller using optimization-based algorithms. This segmentation allows each system to operate within its strengths while reducing communication bandwidth requirements by transferring only essential dense waypoints rather than all control points.
Solution Approach 2:
The patent introduces dense waypoints as an intermediary data structure that bridges the external computer's sampling-based planning and the robot controller's optimization-based refinement. These dense waypoints serve as a compressed representation that conveys essential path information to the controller without requiring transmission of all detailed control points, thus reducing communication bandwidth while maintaining computation flexibility.
2Manufacturing precision
If dense planned waypoints are transferred to the robot controller, then path planning quality is improved, but communication bandwidth consumption increases
Solution Approach 1:
The patent extracts only the essential dense waypoints from the complete motion plan and transfers them to the robot controller, leaving the generation of sparse command points to be performed locally by the controller. This extraction approach maintains high path planning quality by preserving critical path information while significantly reducing the volume of data that must be communicated across the network.
3Speed
If sampling-based method is used to find collision-free path, then computational speed is improved, but path quality may be suboptimal
Solution Approach 1:
The patent applies preliminary action by using sampling-based algorithms on the external computer to quickly generate dense collision-free waypoints before the robot controller performs optimization-based refinement to generate sparse command points. This preliminary generation of feasible paths by sampling methods enables the system to rapidly establish a valid trajectory that can then be optimized for quality, achieving both computational speed and path quality.
Data Source
AI summary
A robot motion planning technique using an external computer communicating with a robot controller. A camera or sensor system provides input scene information including start and goal points and obstacle data to the computer. The computer plans a robot tool motion based on the start and goal points and the obstacle environment, where the robot motion is planned using either a serial or parallel combination of sampling-based and optimization-based planning algorithms. In the serial combination, the sampling method first finds a feasible path, and the optimization method then improves the path quality. In the parallel combination, both sampling and optimization methods are used, and a path is selected based on computation time, path quality and other factors. The computer converts dense planned waypoints to sparse command points for transfer to the robot controller, and the controller computes robot kinematics and interpolation points and controls the movement of the robot.