What Makes a Good Symbol for Hybrid Discrete-Continuous Planning?

Hugging Face Daily Papers Papers
robot-planning symbolic-reasoning hybrid-systems neural-networks optimization interpretability

Summary

本文提出'solver-sufficient symbolization'概念，从推理算法视角定义符号的计算有用性，并开发反例引导的符号发明算法，用于混合离散-连续机器人规划，在仿真与真实机器人任务中降低求解成本同时保持解质量与可解释性。

The physical world has continuous state and action spaces, yet robot planning often benefits from hybrid discrete-continuous formulations that explicitly expose combinatorial structure, such as contact modes or discrete primitive actions. Existing methods typically rely on human-defined symbol sets or symbols derived from language supervision, without asking what makes a symbol computationally useful. In this paper, we take an inference-algorithm--centric view to define usefulness: a good symbol should expose the discrete commitments that simplify solving the original planning problem. We first introduce the concept of solver-sufficient symbolization by studying finite-horizon piecewise-affine systems, for which solver sufficiency can be precisely characterized, and develop a counterexample-guided algorithm for symbol invention. We then extend this principle to invent symbols for optimization objectives parameterized by general neural networks as energy functions, showing that solver-sufficient symbols can nevertheless be induced from their continuous optimization landscapes. Experiments on simulated and real-robot tasks show that the resulting symbols reduce solving cost while preserving solution quality, while also improving interpretability and steerability. Furthermore, our theoretical and algorithmic insights help explain why certain human-defined symbols are computationally useful.
Original Article
View Cached Full Text

Cached at: 10/21/26, 10:23 PM

Paper page - What Makes a Good Symbol for Hybrid Discrete-Continuous Planning?

Source: https://huggingface.co/papers/2610.23010

Abstract

Symbols for robot planning are invented by identifying discrete commitments that simplify solving continuous optimization problems, reducing cost while preserving quality.

The physical world has continuous state and action spaces, yet robot planning often benefits from hybrid discrete-continuous formulations that explicitly expose combinatorial structure, such as contact modes or discrete primitive actions. Existing methods typically rely on human-defined symbol sets or symbols derived from language supervision, without asking what makes a symbol computationally useful. In this paper, we take an inference-algorithm--centric view to define usefulness: a good symbol should expose the discrete commitments that simplify solving the original planning problem. We first introduce the concept ofsolver-sufficient symbolizationby studying finite-horizonpiecewise-affine systems, for which solver sufficiency can be precisely characterized, and develop acounterexample-guided algorithmfor symbol invention. We then extend this principle to invent symbols for optimization objectives parameterized by generalneural networksasenergy functions, showing that solver-sufficient symbols can nevertheless be induced from their continuousoptimization landscapes. Experiments on simulated and real-robot tasks show that the resulting symbols reduce solving cost while preserving solution quality, while also improving interpretability and steerability. Furthermore, our theoretical and algorithmic insights help explain why certain human-defined symbols are computationally useful.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2610\.23010

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.23010 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.23010 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.23010 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles