Momentum-constrained Hybrid Heuristic Trajectory Optimization Framework with Residual-enhanced DRL for Visually Impaired Scenarios

2025-09-19

AI Summary

To address the challenge of simultaneously ensuring trajectory smoothness, safety, and real-time performance in vision-impaired assistive navigation, this paper proposes a momentum-constrained hybrid heuristic trajectory optimization framework. Methodologically, it integrates Frenet-coordinate-based sampling optimization with a residual-enhanced LSTM-PPO reinforcement learning module, enabling semantic intent alignment and adaptive trajectory refinement under a two-stage cost modeling scheme. Kinematic feasibility is guaranteed via third-order interpolated quintic polynomials and bidirectional Frenet–Cartesian coordinate transformation. Compared to baseline approaches, the proposed method achieves a 50% faster training convergence, reduces average planning cost by 30.3%, decreases cost variance by 53.3%, and lowers ego-vehicle–obstacle collision risk by over 77%. These improvements significantly enhance system robustness and practical deployability in real-world assistive navigation scenarios.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper proposes a momentum-constrained hybrid heuristic trajectory optimization framework (MHHTOF) tailored for assistive navigation in visually impaired scenarios, integrating trajectory sampling generation, optimization and evaluation with residual-enhanced deep reinforcement learning (DRL). In the first stage, heuristic trajectory sampling cluster (HTSC) is generated in the Frenet coordinate system using third-order interpolation with fifth-order polynomials and momentum-constrained trajectory optimization (MTO) constraints to ensure smoothness and feasibility. After first stage cost evaluation, the second stage leverages a residual-enhanced actor-critic network with LSTM-based temporal feature modeling to adaptively refine trajectory selection in the Cartesian coordinate system. A dual-stage cost modeling mechanism (DCMM) with weight transfer aligns semantic priorities across stages, supporting human-centered optimization. Experimental results demonstrate that the proposed LSTM-ResB-PPO achieves significantly faster convergence, attaining stable policy performance in approximately half the training iterations required by the PPO baseline, while simultaneously enhancing both reward outcomes and training stability. Compared to baseline method, the selected model reduces average cost and cost variance by 30.3% and 53.3%, and lowers ego and obstacle risks by over 77%. These findings validate the framework's effectiveness in enhancing robustness, safety, and real-time feasibility in complex assistive planning tasks.

Problem

• Optimizing assistive navigation trajectories for visually impaired users
• Integrating momentum constraints with deep reinforcement learning
• Enhancing safety and robustness in complex assistive planning

Innovation

• Momentum-constrained hybrid heuristic trajectory optimization framework
• Residual-enhanced deep reinforcement learning with LSTM
• Dual-stage cost modeling with weight transfer