Neural signed distance functions speed up safer robot arm motion planning
Funnel planning and control for manipulators using neural Signed Configuration Distance Functions
Robotics
Summary
Safe and efficient movement of robot arms is important but hard to guarantee, especially when unexpected disturbances happen. The authors improve a method that ensures robot arms stay in safe regions during their movement by using a neural network to quickly estimate how far the robot is from obstacles. This helps plan faster and safer paths, while keeping the robot well clear of collisions. Their experiments show faster path planning and better control compared to older methods.
What this means in practice
- •For robotic system engineers: Enable faster and safer path planning for robot arms by efficiently estimating collision-free regions using neural signed distance functions.
- •For industrial automation teams: Improve robustness and clearance in robot manipulator control to reduce downtime and collisions during manufacturing tasks.
Authors
Bernhard Wullt, Christos K. Verginis, Per Mattsson, Mikael Norrlöf, Thomas B. Schön
Abstract
Robust motion planning and control for manipulators is the problem of guaranteeing safe execution and collision-free motion under disturbances. The Kinodynamic Motion Planning via Funnel Control (KDF) is a recently proposed planner that comes with robustness guarantees and is particularly attractive for collision-free control as it guarantees closed-loop evolution inside a funnel, i.e., a collision-free region around a nominal trajectory. Despite its attractive theoretical properties, the current approach for computing funnels is computationally demanding, which limits its expressiveness and performance. We address its current limitations by proposing a novel funnel planning and control solution. Our key tool to enable this is a neural Signed Configuration Distance Function (nSCDF) which allows us to estimate collision-free balls and gradients in a computationally efficient way. We use the nSCDF in our planner to compute a nominal trajectory, where path length and clearance are balanced. To track the trajectory with collision-avoidance guarantees, we design a funnel controller that exploits the geometric information from the nSCDF. From numerical experiments, we observe that our planner produces nominal paths $2$ times faster, while at the same time obtaining $20 \%$ shorter path length and $5$ times the clearance. Finally, we also observe improved motion performance and robustness properties when using the nSCDF for funnel control.