Robot Joint Trajectory Caching for Low-Latency Motion Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robot arm motion planning is computationally expensive due to the complexity of finding collision-free joint trajectories, especially in dynamic environments with unknown obstacles, leading to suboptimal solutions when calculated in real time.
Innovation Solution
Pre-calculating optimized joint trajectories offline using more resource-intensive methods like RRT* and storing them in a database for later use, allowing robots to leverage pre-calculated paths for repetitive tasks, reducing real-time planning latency and resource waste.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If resource-intensive trajectory planning methods (e.g., RRT*) are used in real time, then joint trajectory quality is improved, but latency in robot operation increases to unacceptable levels
Solution Approach 1:
The system performs complex trajectory planning computations in advance (offline) when the robot is not in operation, storing precalculated joint trajectories for later use. This preliminary action transfers the computational burden from real-time operation to idle periods, enabling high-quality trajectories without real-time latency
Solution Approach 2:
The system creates copies of precalculated joint trajectories and stores them in a database for rapid retrieval during operation. Instead of recalculating optimal trajectories in real time, the robot retrieves precomputed trajectory copies that have already been optimized using resource-intensive methods
2Productivity
If sampling-based methods with random or quasi-random joint configurations are used, then planning time is reduced, but joint trajectory solutions become suboptimal with little concern for robot wear-and-tear
Solution Approach 1:
The system uses offline computation periods to perform thorough, optimal trajectory planning that considers robot wear-and-tear and other optimization criteria. This preliminary optimal planning eliminates the need to use suboptimal fast methods during operation
3Reliability
If computationally expensive collision-checking is performed repeatedly for each trajectory calculation, then collision-free trajectories are found, but computing resources are wasted on repetitive tasks
Solution Approach 1:
The system caches precalculated joint trajectories in a database, allowing the robot to retrieve and reuse proven collision-free trajectories without performing repeated collision-checking computations. This copying approach maintains safety while eliminating redundant computational work
Data Source
AI summary
Implementations are described herein for offline computation and caching of precalculated joint trajectories. In various implementations, an instruction may be obtained to move an end effector of a robot between start and target positions. A first type of trajectory planning may be performed in real time or “online” to calculate a first joint trajectory of the robot that moves the end effector from the start to target position. The robot may then implement the first joint trajectory. A second type of trajectory planning may be performed offline, e.g., during downtime of the robot, to precalculate a second joint trajectory of the robot to move the end effector from the start to target position. The second type of trajectory planning may require more resources than were required by the first type of trajectory planning. Data indicative of the precalculated second joint trajectory of the robot may be stored for future use.