SocialNav-Map: Dynamic Mapping with Human Trajectory Prediction for Zero-Shot Social Navigation

TL;DR

SocialNav-Map introduces a zero-shot social navigation framework that predicts human trajectories and constructs dynamic occupancy maps, enabling safe, efficient navigation without environment-specific training, outperforming existing RL-based methods.

Contribution

It combines human trajectory prediction with occupancy mapping to enable zero-shot social navigation, eliminating the need for extensive environment-specific training.

Findings

Reduces human collision rates by over 10% in experiments.

Outperforms state-of-the-art RL-based methods on benchmark datasets.

Requires no training in new environments, enabling practical deployment.

Abstract

Social navigation in densely populated dynamic environments poses a significant challenge for autonomous mobile robots, requiring advanced strategies for safe interaction. Existing reinforcement learning (RL)-based methods require over 2000+ hours of extensive training and often struggle to generalize to unfamiliar environments without additional fine-tuning, limiting their practical application in real-world scenarios. To address these limitations, we propose SocialNav-Map, a novel zero-shot social navigation framework that combines dynamic human trajectory prediction with occupancy mapping, enabling safe and efficient navigation without the need for environment-specific training. Specifically, SocialNav-Map first transforms the task goal position into the constructed map coordinate system. Subsequently, it creates a dynamic occupancy map that incorporates predicted human movements as dynamic obstacles. The framework employs two complementary methods for human trajectory prediction: history prediction and orientation prediction. By integrating these predicted trajectories into the occupancy map, the robot can proactively avoid potential collisions with humans while efficiently navigating to its destination. Extensive experiments on the Social-HM3D and Social-MP3D datasets demonstrate that SocialNav-Map significantly outperforms state-of-the-art (SOTA) RL-based methods, which require 2,396 GPU hours of training. Notably, it reduces human collision rates by over 10% without necessitating any training in novel environments. By eliminating the need for environment-specific training, SocialNav-Map achieves superior navigation performance, paving the way for the deployment of social navigation systems in real-world environments characterized by diverse human behaviors. The code is available at: https://github.com/linglingxiansen/SocialNav-Map.