Learning Maximal Safe Sets Using Hypernetworks for MPC-based Local Trajectory Planning in Unknown Environments

2024-10-26

AI Summary

This work addresses the challenges of recursive feasibility and safety in local trajectory planning for unknown static environments. We propose a real-time maximum safe set estimation method based on hypernetworks. Leveraging Hamilton–Jacobi reachability analysis as a supervisory signal and integrating neural implicit set representations, our approach is the first to enable end-to-end learning—via hypernetworks—of the maximum safe set under general nonlinear dynamics and arbitrary constraints; this learned set is embedded into an MPC framework as a terminal constraint. In simulation, our method achieves a 52% higher task success rate than conventional approaches while maintaining inference speed comparable to baselines. Real-world experiments demonstrate robust obstacle avoidance in complex cluttered scenes where baseline methods fail. The core contribution is the introduction of a hypernetwork-driven safe set learning paradigm, unifying formal reachability guarantees with data-driven generalization capability.

Technology Category

• Natural Language Processing: Safety and Robustness
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

This paper presents a novel learning-based approach for online estimation of maximal safe sets for local trajectory planning in unknown static environments. The neural representation of a set is used as the terminal set constraint for a model predictive control (MPC) local planner, resulting in improved recursive feasibility and safety. To achieve real-time performance and desired generalization properties, we employ the idea of hypernetworks. We use the Hamilton-Jacobi (HJ) reachability analysis as the source of supervision during the training process, allowing us to consider general nonlinear dynamics and arbitrary constraints. The proposed method is extensively evaluated against relevant baselines in simulations for different environments and robot dynamics. The results show a success rate increase of up to 52 % compared to the best baseline while maintaining comparable execution speed. Additionally, we deploy our proposed method, NTC-MPC, on a physical robot and demonstrate its ability to safely avoid obstacles in scenarios where the baselines fail.

Problem

• Online estimation of maximal safe sets for trajectory planning in unknown environments.
• Improved recursive feasibility and safety using neural set representation in MPC.
• Real-time performance and generalization via hypernetworks and HJ reachability analysis.

Innovation

• Hypernetworks for real-time safe set estimation
• HJ reachability analysis for training supervision
• NTC-MPC for improved safety and feasibility