Self-Supervised Path Planning in Unstructured Environments via Global-Guided Differentiable Hard Constraint Projection

TL;DR

This paper introduces a self-supervised neural framework with a differentiable projection layer and global-guided supervision for safe, real-time path planning in unstructured environments, suitable for embedded systems.

Contribution

It presents a novel self-supervised approach with a differentiable hard constraint projection and global-guided artificial potential field for efficient, safe path planning in resource-limited settings.

Findings

Achieved 88.75% success rate on 20,000 scenarios.

Validated real-time path planning on NVIDIA Jetson Orin NX.

Demonstrated safety and feasibility in CARLA simulations.

Abstract

Deploying deep learning agents for autonomous navigation in unstructured environments faces critical challenges regarding safety, data scarcity, and limited computational resources. Traditional solvers often suffer from high latency, while emerging learning-based approaches struggle to ensure deterministic feasibility. To bridge the gap from embodied to embedded intelligence, we propose a self-supervised framework incorporating a differentiable hard constraint projection layer for runtime assurance. To mitigate data scarcity, we construct a Global-Guided Artificial Potential Field (G-APF), which provides dense supervision signals without manual labeling. To enforce actuator limitations and geometric constraints efficiently, we employ an adaptive neural projection layer, which iteratively rectifies the coarse network output onto the feasible manifold. Extensive benchmarks on a test set of 20,000 scenarios demonstrate an 88.75\% success rate, substantiating the enhanced operational safety. Closed-loop experiments in CARLA further validate the physical realizability of the planned paths under dynamic constraints. Furthermore, deployment verification on an NVIDIA Jetson Orin NX confirms an inference latency of 94 ms, showing real-time feasibility on resource-constrained embedded hardware. This framework offers a generalized paradigm for embedding physical laws into neural architectures, providing a viable direction for solving constrained optimization in mechatronics. Source code is available at: https://github.com/wzq-13/SSHC.git.