Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories
This addresses the problem of inefficient and uninterpretable robot policies for long-horizon tasks, offering a structured and sample-efficient solution.
The paper tackles the challenge of scaling robot learning to long-horizon tasks by introducing ENAP, a framework that learns a bi-level neuro-symbolic policy from visuomotor demonstrations, achieving up to 27% improvement over state-of-the-art end-to-end policies in low-data regimes.
Scaling robot learning to long-horizon tasks remains a formidable challenge. While end-to-end policies often lack the structural priors needed for effective long-term reasoning, traditional neuro-symbolic methods rely heavily on hand-crafted symbolic priors. To address the issue, we introduce ENAP (Emergent Neural Automaton Policy), a framework that allows a bi-level neuro-symbolic policy adaptively emerge from visuomotor demonstrations. Specifically, we first employ adaptive clustering and an extension of the L* algorithm to infer a Mealy state machine from visuomotor data, which serves as an interpretable high-level planner capturing latent task modes. Then, this discrete structure guides a low-level reactive residual network to learn precise continuous control via behavior cloning (BC). By explicitly modeling the task structure with discrete transitions and continuous residuals, ENAP achieves high sample efficiency and interpretability without requiring task-specific labels. Extensive experiments on complex manipulation and long-horizon tasks demonstrate that ENAP outperforms state-of-the-art (SoTA) end-to-end VLA policies by up to 27% in low-data regimes, while offering a structured representation of robotic intent (Fig. 1).