Latent Perspective-Taking via a Schrödinger Bridge in Influence-Augmented Local Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alcedo, Kevin, Lima, Pedro U., Alami, Rachid
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908807898071040
author Alcedo, Kevin
Lima, Pedro U.
Alami, Rachid
author_facet Alcedo, Kevin
Lima, Pedro U.
Alami, Rachid
contents Operating in environments alongside humans requires robots to make decisions under uncertainty. In addition to exogenous dynamics, they must reason over others' hidden mental-models and mental-states. While Interactive POMDPs and Bayesian Theory of Mind formulations are principled, exact nested-belief inference is intractable, and hand-specified models are brittle in open-world settings. We address both by learning structured mental-models and an estimator of others' mental-states. Building on the Influence-Based Abstraction, we instantiate an Influence-Augmented Local Model to decompose socially-aware robot tasks into local dynamics, social influences, and exogenous factors. We propose (a) a neuro-symbolic world model instantiating a factored, discrete Dynamic Bayesian Network, and (b) a perspective-shift operator modeled as an amortized Schrödinger Bridge over the learned local dynamics that transports factored egocentric beliefs into other-centric beliefs. We show that this architecture enables agents to synthesize socially-aware policies in model-based reinforcement learning, via decision-time mental-state planning (a Schrödinger Bridge in belief space), with preliminary results in a MiniGrid social navigation task.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02857
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Latent Perspective-Taking via a Schrödinger Bridge in Influence-Augmented Local Models
Alcedo, Kevin
Lima, Pedro U.
Alami, Rachid
Robotics
Operating in environments alongside humans requires robots to make decisions under uncertainty. In addition to exogenous dynamics, they must reason over others' hidden mental-models and mental-states. While Interactive POMDPs and Bayesian Theory of Mind formulations are principled, exact nested-belief inference is intractable, and hand-specified models are brittle in open-world settings. We address both by learning structured mental-models and an estimator of others' mental-states. Building on the Influence-Based Abstraction, we instantiate an Influence-Augmented Local Model to decompose socially-aware robot tasks into local dynamics, social influences, and exogenous factors. We propose (a) a neuro-symbolic world model instantiating a factored, discrete Dynamic Bayesian Network, and (b) a perspective-shift operator modeled as an amortized Schrödinger Bridge over the learned local dynamics that transports factored egocentric beliefs into other-centric beliefs. We show that this architecture enables agents to synthesize socially-aware policies in model-based reinforcement learning, via decision-time mental-state planning (a Schrödinger Bridge in belief space), with preliminary results in a MiniGrid social navigation task.
title Latent Perspective-Taking via a Schrödinger Bridge in Influence-Augmented Local Models
topic Robotics
url https://arxiv.org/abs/2602.02857