A New Trajectory-Oriented Approach to Enhancing Comprehensive Crowd Navigation Performance

TL;DR

This paper tackles the challenge of fairly evaluating DRL-based crowd navigation by introducing a multi-objective, curvature-focused framework that explicitly quantifies trajectory continuity. It presents a comprehensive indicator system, a new trajectory-quality metric based on curvature differences, and a curvature-aware reward shaping approach implemented within a continuous-action PPO framework. Through extensive 2D experiments across low and high pedestrian densities and preliminary 3D verification, the method demonstrates improved safety, success, and trajectory quality with notable gains in efficiency and robustness. The work highlights the importance of trajectory continuity for naturalness, comfort, and energy efficiency, while acknowledging sim-to-real challenges and outlining future work in realistic 3D training and end-to-end models.

Abstract

Crowd navigation has garnered considerable research interest in recent years, especially with the proliferating application of deep reinforcement learning (DRL) techniques. Many studies, however, do not sufficiently analyze the relative priorities among evaluation metrics, which compromises the fair assessment of methods with divergent objectives. Furthermore, trajectory-continuity metrics, specifically those requiring $C^2$ smoothness, are rarely incorporated. Current DRL approaches generally prioritize efficiency and proximal comfort, often neglecting trajectory optimization or addressing it only through simplistic, unvalidated smoothness reward. Nevertheless, effective trajectory optimization is essential to ensure naturalness, enhance comfort, and maximize the energy efficiency of any navigation system. To address these gaps, this paper proposes a unified framework that enables the fair and transparent assessment of navigation methods by examining the prioritization and joint evaluation of multiple optimization objectives. We further propose a novel reward-shaping strategy that explicitly emphasizes trajectory-curvature optimization. The resulting trajectory quality and adaptability are significantly enhanced across multi-scale scenarios. Through extensive 2D and 3D experiments, we demonstrate that the proposed method achieves superior performance compared to state-of-the-art approaches.

Figures (7)

• Figure 1: Impact of trajectory continuity on crowd navigation.
• Figure 2: Schematic diagram of trajectories with different levels of continuity ravankar2018path. (a) Discontinuous trajectory. (b) $C^0$ continuity. (c)$C^1$ continuity. (d) $C^2$ continuity.
• Figure 3: The schematic diagram of PPO training process for crowd navigation.
• Figure 4: The difference between the impact of continuous action space and discrete action space on trajectory.
• Figure 5: 2D Simulation Environment.