Constructing the Umwelt: Cognitive Planning through Belief-Intent Co-Evolution

TL;DR

This paper introduces a novel cognitive planning architecture for autonomous driving that emphasizes belief-intent co-evolution and cognitive consistency, challenging the need for high-fidelity world reconstruction.

Contribution

It proposes the Mental Bayesian Causal World Model and Tokenized Intent World Model, integrating cognitive science principles into end-to-end planning for improved performance and human-like behaviors.

Findings

Enhanced planning performance in open-loop validation.

Emergent human-like cognitive behaviors in closed-loop simulations.

Semantic alignment achieved through belief and intent co-evolution.

Abstract

This paper challenges a prevailing epistemological assumption in End-to-End Autonomous Driving: that high-performance planning necessitates high-fidelity world reconstruction. Inspired by cognitive science, we propose the Mental Bayesian Causal World Model (MBCWM) and instantiate it as the Tokenized Intent World Model (TIWM), a novel cognitive computing architecture. Its core philosophy posits that intelligence emerges not from pixel-level objective fidelity, but from the Cognitive Consistency between the agent's internal intentional world and physical reality. By synthesizing von Uexk\"ull's $\textit{Umwelt}$ theory, the neural assembly hypothesis, and the triple causal model (integrating symbolic deduction, probabilistic induction, and force dynamics) into an end-to-end embodied planning system, we demonstrate the feasibility of this paradigm on the nuPlan benchmark. Experimental results in open-loop validation confirm that our Belief-Intent Co-Evolution mechanism effectively enhances planning performance. Crucially, in closed-loop simulations, the system exhibits emergent human-like cognitive behaviors, including map affordance understanding, free exploration, and self-recovery strategies. We identify Cognitive Consistency as the core learning mechanism: during long-term training, belief (state understanding) and intent (future prediction) spontaneously form a self-organizing equilibrium through implicit computational replay, achieving semantic alignment between internal representations and physical world affordances. TIWM offers a neuro-symbolic, cognition-first alternative to reconstruction-based planners, establishing a new direction: planning as active understanding, not passive reaction.