# Language-Guided Terrain-Adaptive Neural MPC for Autonomous Traversal of Articulated Tracked Robots

arXiv: https://arxiv.org/abs/2609.13083 · HTML: https://mlsanity.com/paper/2609.13083/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [acados: a modular open-source framework for fast embedded optimal control](https://mlsanity.com/paper/1910.13753/) (2019)
- [Real-time Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platforms](https://mlsanity.com/paper/2203.07747/) (2022)
- [OptiMUS: Optimization Modeling Using MIP Solvers and large language models](https://mlsanity.com/paper/2310.06116/) (2023)
- [VLMPC: Vision-Language Model Predictive Control for Robotic Manipulation](https://mlsanity.com/paper/2407.09829/) (2024)
- [KNODE-MPC: A Knowledge-based Data-driven Predictive Control Framework for Aerial Robots](https://mlsanity.com/paper/2109.04821/) (2021)
- [Learning to Learn Faster from Human Feedback with Language Model Predictive Control](https://mlsanity.com/paper/2402.11450/) (2024)
- [HPIPM: a high-performance quadratic programming framework for model predictive control](https://mlsanity.com/paper/2003.02547/) (2020)
- [Learning for CasADi: Data-driven Models in Numerical Optimization](https://mlsanity.com/paper/2312.05873/) (2023)
- [Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models](https://mlsanity.com/paper/2504.11514/) (2025)
- [Learning Model Predictive Control with Error Dynamics Regression for Autonomous Racing](https://mlsanity.com/paper/2309.10716/) (2023)
- [Hybrid Systems Differential Dynamic Programming for Whole-Body Motion Planning of Legged Robots](https://mlsanity.com/paper/2006.08102/) (2020)
- [Data-driven Policy Transfer with Imprecise Perception Simulation](https://mlsanity.com/paper/1804.01953/) (2018)
- [Flexible Disaster Response of Tomorrow -- Final Presentation and Evaluation of the CENTAURO System](https://mlsanity.com/paper/1909.08812/) (2019)
- [Hybrid Trajectory Optimization for Autonomous Terrain Traversal of Articulated Tracked Robots](https://mlsanity.com/paper/2306.02659/) (2023)
- [Adaptive Model Predictive Control with Data-driven Error Model for Quadrupedal Locomotion](https://mlsanity.com/paper/2407.10124/) (2024)
- [NPC: Neural Predictive Control for Fuel-Efficient Autonomous Trucks](https://mlsanity.com/paper/2412.13618/) (2024)

## Abstract (arXiv)

In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and cluttered building interiors. Reliable autonomy remains challenging because robot-terrain interaction (RTI) is hybrid and discontinuous, and effective flipper-track coordination is difficult to model analytically. We present ASTRIL-MPC, a language-guided neural kinematics model predictive control (MPC) framework for autonomous traversal. A learned kinematics model predicts short-horizon task-state increments from a height sequence and recent trajectories; NMPC plans with multi-objective costs and strict feasibility constraints; and a large language model (LLM) proposes bounded updates to selected weights and bounds through a safety-checked interface with range clipping, rate limiting, and consistency checks. The compiled predictor enables a full control cycle within 100 ms. Across three traversal tasks and a multi-height generalization setting, ASTRIL-MPC improves an aggregate traversal-quality score by up to 71% over a non-adaptive NMPC and by 67% over a PPO baseline, while eliminating measurable collision impacts during descent. These results indicate that combining terrain-conditioned neural kinematics, optimization-based planning, and language-guided adaptation yields data-efficient and robust autonomy for articulated tracked robots. Real-robot trials over four indoor obstacles further demonstrate transfer to contact-rich physical traversal.