Neural Collision Clearance Estimator for Batched Motion Planning
This addresses the bottleneck of computational efficiency in motion planning for robotics, particularly in cluttered environments with high degrees of freedom, representing an incremental improvement over existing methods.
The paper tackles the problem of slow collision checking in high-dimensional motion planning by introducing ClearanceNet, a neural network that predicts separation distances, achieving an 845x speedup over traditional methods, and CN-RRT, a planning algorithm that uses this to accelerate planning by up to 42% and find paths up to 36% more efficient.
We present a neural network collision checking heuristic, ClearanceNet, and a planning algorithm, CN-RRT. ClearanceNet learns to predict separation distance (minimum distance between robot and workspace) with respect to a workspace. CN-RRT then efficiently computes a motion plan by leveraging three key features of ClearanceNet. First, CN-RRT explores the space by expanding multiple nodes at the same time, processing batches of thousands of collision checks. Second, CN-RRT adaptively relaxes its clearance requirements for more difficult problems. Third, to repair errors, CN-RRT shifts its nodes in the direction of ClearanceNet's gradient and repairs any residual errors with a traditional RRT, thus maintaining theoretical probabilistic completeness guarantees. In configuration spaces with up to 30 degrees of freedom, ClearanceNet achieves 845x speedup over traditional collision detection methods, while CN-RRT accelerates motion planning by up to 42% over a baseline and finds paths up to 36% more efficient. Experiments on an 11 degree of freedom robot in a cluttered environment confirm the method's feasibility on real robots.