Perspective-Shifted Neuro-Symbolic World Models: A Framework for Socially-Aware Robot Navigation
On the map: World models → World models for navigation
Abstract (arXiv)
Navigating in environments alongside humans requires agents to reason under uncertainty and account for the beliefs and intentions of those around them. Under a sequential decision-making framework, egocentric navigation can naturally be represented as a Markov Decision Process (MDP). However, social navigation additionally requires reasoning about the hidden beliefs of others, inherently leading to a Partially Observable Markov Decision Process (POMDP), where agents lack direct access to others' mental states. Inspired by Theory of Mind and Epistemic Planning, we propose (1) a neuro-symbolic model-based reinforcement learning architecture for social navigation, addressing the challenge of belief tracking in partially observable environments; and (2) a perspective-shift operator for belief estimation, leveraging recent work on Influence-based Abstractions (IBA) in structured multi-agent settings.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for navigation, one of 11 directions in World models. Builds on 16 of its 33 references that are in the map. First posted on arXiv 26 Mar 2025.
Builds on
16 of 33 references.
References · 16
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
- 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
- 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
- 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
- 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
- 2018Recurrent World Models Facilitate Policy Evolutioncited by 785
- 2022DayDreamer: World Models for Physical Robot Learningcited by 400
- 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
- 2018State Representation Learning for Control: An Overviewcited by 127
- 2023Principles and Guidelines for Evaluating Social Robot Navigation Algorithmscited by 56
- 2022Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graphcited by 53
- 2023A Survey on Socially Aware Robot Navigation: Taxonomy and Future Challengescited by 39
4 more
- 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24
- 2019A Sufficient Statistic for Influence in Structured Multiagent Environmentscited by 8
- 2017Viewing Robot Navigation in Human Environment as a Cooperative Activitycited by 4
- 2022Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systemscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Latent Perspective-Taking via a Schr"odinger Bridge in Influence-Augmented Local Models ↗
- 2025Socially aware navigation for mobile robots: a survey on deep reinforcement learning approaches
- 2025SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation
- 2025Logic-Guided Socially-aware Robot Navigation World Model
- 2026Vision-Language Models for Deployable Social Robot Navigation: Bridging Semantic Reasoning and Low-Level Control
- 2025MAction-SocialNav: Multi-Action Socially Compliant Navigation via Reasoning-enhanced Prompt Tuning
- 2026NavThinker: Action-Conditioned World Models for Coupled Prediction and Planning in Social Navigation
- 2024Belief Aided Navigation using Bayesian Reinforcement Learning for Avoiding Humans in Blind Spots