# Don't Just Search, Understand: Semantic Path Planning Agent for Spherical Tensegrity Robots in Unknown Environments

arXiv: https://arxiv.org/abs/2511.01236 · HTML: https://mlsanity.com/paper/2511.01236/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 39 references that are in the map.
- First posted on arXiv 3 Nov 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 15 of 15)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models](https://mlsanity.com/paper/2305.16986/) (2023)
- [AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers](https://mlsanity.com/paper/2306.06531/) (2023)
- [Consciousness in Artificial Intelligence: Insights from the Science of Consciousness](https://mlsanity.com/paper/2308.08708/) (2023)
- [Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments](https://mlsanity.com/paper/1612.05533/) (2016)
- [Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning](https://mlsanity.com/paper/2310.03249/) (2023)
- [LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning](https://mlsanity.com/paper/2407.02511/) (2024)
- [Batch Informed Trees (BIT*): Sampling-based Optimal Planning via the Heuristically Guided Search of Implicit Random Geometric Graphs](https://mlsanity.com/paper/1405.5848/) (2014)
- [Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns](https://mlsanity.com/paper/2404.14812/) (2024)
- [Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans](https://mlsanity.com/paper/1911.03074/) (2019)
- [Deep Reinforcement Learning for Tensegrity Robot Locomotion](https://mlsanity.com/paper/1609.09049/) (2016)
- [Sampling-based Algorithms for Optimal Motion Planning Using Closed-loop Prediction](https://mlsanity.com/paper/1601.06326/) (2016)
- [Inclined Surface Locomotion Strategies for Spherical Tensegrity Robots](https://mlsanity.com/paper/1708.08150/) (2017)

## Abstract (arXiv)

Endowed with inherent dynamical properties that grant them remarkable ruggedness and adaptability, spherical tensegrity robots stand as prototypical examples of hybrid softrigid designs and excellent mobile platforms. However, path planning for these robots in unknown environments presents a significant challenge, requiring a delicate balance between efficient exploration and robust planning. Traditional path planners, which treat the environment as a geometric grid, often suffer from redundant searches and are prone to failure in complex scenarios due to their lack of semantic understanding. To overcome these limitations, we reframe path planning in unknown environments as a semantic reasoning task. We introduce a Semantic Agent for Tensegrity robots (SATPlanner) driven by a Large Language Model (LLM). SATPlanner leverages high-level environmental comprehension to generate efficient and reliable planning strategies.At the core of SATPlanner is an Adaptive Observation Window mechanism, inspired by the "fast" and "slow" thinking paradigms of LLMs. This mechanism dynamically adjusts the perceptual field of the agent: it narrows for rapid traversal of open spaces and expands to reason about complex obstacle configurations. This allows the agent to construct a semantic belief of the environment, enabling the search space to grow only linearly with the path length (O(L)) while maintaining path quality. We extensively evaluate SATPlanner in 1,000 simulation trials, where it achieves a 100% success rate, outperforming other real-time planning algorithms. Critically, SATPlanner reduces the search space by 37.2% compared to the A* algorithm while achieving comparable, near-optimal path lengths. Finally, the practical feasibility of SATPlanner is validated on a physical spherical tensegrity robot prototype.