Neural Potential Field for Obstacle-Aware Local Motion Planning
This work addresses a specific challenge in mobile robotics for real-time obstacle-aware motion planning, presenting an incremental improvement by integrating neural networks into model predictive control.
The authors tackled the problem of representing collision costs for arbitrary obstacle maps and robot footprints in local motion planning by proposing a Neural Potential Field, a differentiable neural network model that enables real-time, safe planning with trajectories that have superior smoothness and comparable path length to existing methods.
Model predictive control (MPC) may provide local motion planning for mobile robotic platforms. The challenging aspect is the analytic representation of collision cost for the case when both the obstacle map and robot footprint are arbitrary. We propose a Neural Potential Field: a neural network model that returns a differentiable collision cost based on robot pose, obstacle map, and robot footprint. The differentiability of our model allows its usage within the MPC solver. It is computationally hard to solve problems with a very high number of parameters. Therefore, our architecture includes neural image encoders, which transform obstacle maps and robot footprints into embeddings, which reduce problem dimensionality by two orders of magnitude. The reference data for network training are generated based on algorithmic calculation of a signed distance function. Comparative experiments showed that the proposed approach is comparable with existing local planners: it provides trajectories with outperforming smoothness, comparable path length, and safe distance from obstacles. Experiment on Husky UGV mobile robot showed that our approach allows real-time and safe local planning. The code for our approach is presented at https://github.com/cog-isa/NPField together with demo video.