Optimal-Horizon Social Robot Navigation in Heterogeneous Crowds

TL;DR

An optimal-horizon social navigation framework that optimizes MPC foresight online according to inferred social context is proposed that achieves a 6.8% improvement in success rate, reduces collisions by 50%, and shortens navigation time by 19%, validating the necessity of socially optimal planning horizons for efficient and safe robot navigation in crowded environments.

Abstract

Navigating social robots in dense, dynamic crowds is challenging due to environmental uncertainty and complex human-robot interactions. While Model Predictive Control (MPC) offers strong real-time performance, its reliance on a fixed prediction horizon limits adaptability to changing environments and social dynamics. Furthermore, most MPC approaches treat pedestrians as homogeneous obstacles, ignoring social heterogeneity and cooperative or adversarial interactions, which often causes the Frozen Robot Problem in partially observable real-world environments. In this paper, we identify the planning horizon as a socially conditioned decision variable rather than a fixed design choice. Building on this insight, we propose an optimal-horizon social navigation framework that optimizes MPC foresight online according to inferred social context. A spatio-temporal Transformer infers pedestrian cooperation attributes from local trajectory observations, which serve as social priors for a reinforcement learning policy that optimally selects the prediction horizon under a task-driven objective. The resulting horizon-aware MPC incorporates socially conditioned safety constraints to balance navigation efficiency and interaction safety. Extensive simulations and real-world robot experiments demonstrate that optimal foresight selection is critical for robust social navigation in partially observable crowds. Compared to state-of-the-art baselines, the proposed approach achieves a 6.8\% improvement in success rate, reduces collisions by 50\%, and shortens navigation time by 19\%, with a low timeout rate of 0.8\%, validating the necessity of socially optimal planning horizons for efficient and safe robot navigation in crowded environments. Code and videos are available at Under Review.

Figures (6)

• Figure 1: Navigation success rates under fixed MPC prediction horizons, averaged over 250 random trials. Solid lines indicate the average performance, while vertical error bars represent performance variations across different pedestrian behavior modes. Note that the low-interaction scenario lacks error bars as all pedestrians are consistently non-cooperative, resulting in a single behavior mode.
• Figure 2: Overview of the Optimal-Horizon Social Robot Navigation framework. Stage I: The Spatio-Temporal Transformer infers pedestrian cooperation attributes $c_t^p$ from trajectory history. Stage II: The RL policy determines the optimal prediction horizon $h_t$ based on the inferred social graph $G_t$. Stage III: The DTCBF-constrained MPC generates safe, socially-compliant control commands $u_t^*$ by adapting its look-ahead depth and safety margins.
• Figure 3: Trajectories of all methods in low-interaction scenarios. All pedestrians in low-interaction scenarios are non-cooperative. The golden solid circles represent robot trajectories with timestamps. The hollow circles in different colors represent pedestrians, with pedestrian IDs shown at start and end points.
• Figure 4: Illustration of the navigation trajectory of ORCA and our proposed method in mid-interaction scenarios.
• Figure 5: Illustration of the navigation trajectory of GST-RL and our proposed method in high-interaction scenarios.