NavThinker: Action-Conditioned World Models for Coupled Prediction and Planning in Social Navigation

TL;DR

NavThinker introduces a future-aware framework for social navigation that couples an action-conditioned world model with reinforcement learning, enabling robots to predict scene evolution and plan safer, more effective paths in dynamic human environments.

Contribution

It proposes a novel action-conditioned world model operating in feature space, integrated with reinforcement learning for coupled prediction and planning in social navigation.

Findings

Achieves state-of-the-art success in social navigation tasks.

Demonstrates effective zero-shot transfer to unseen environments.

Validates real-world deployment on a mobile robot.

Abstract

Social navigation requires robots to act safely in dynamic human environments. Effective behavior demands thinking ahead: reasoning about how the scene and pedestrians evolve under different robot actions rather than reacting to current observations alone. This creates a coupled prediction-planning challenge, where robot actions and human motion mutually influence each other. To address this challenge, we propose NavThinker, a future-aware framework that couples an action-conditioned world model with on-policy reinforcement learning. The world model operates in the Depth Anything V2 patch feature space and performs autoregressive prediction of future scene geometry and human motion; multi-head decoders then produce future depth maps and human trajectories, yielding a future-aware state aligned with traversability and interaction risk. Crucially, we train the policy with DD-PPO while injecting world-model think-ahead signals via: (i) action-conditioned future features fused into the current observation embedding and (ii) social reward shaping from predicted human trajectories. Experiments on single- and multi-robot Social-HM3D show state-of-the-art navigation success, with zero-shot transfer to Social-MP3D and real-world deployment on a Unitree Go2, validating generalization and practical applicability. Webpage: https://hutslib.github.io/NavThinker.