# Constrained Decoding for Safe Robot Navigation Foundation Models

arXiv: https://arxiv.org/abs/2509.01728 · HTML: https://mlsanity.com/paper/2509.01728/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 30 of 30)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models](https://mlsanity.com/paper/2406.16838/) (2024)
- [Prompting Is Programming: A Query Language for Large Language Models](https://mlsanity.com/paper/2212.06094/) (2022)
- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion](https://mlsanity.com/paper/2401.17583/) (2024)
- [PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators](https://mlsanity.com/paper/2406.20083/) (2024)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning](https://mlsanity.com/paper/2409.16578/) (2024)
- [SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World](https://mlsanity.com/paper/2312.02976/) (2023)
- [Generating Robot Constitutions & Benchmarks for Semantic Safety](https://mlsanity.com/paper/2503.08663/) (2025)
- [SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models](https://mlsanity.com/paper/2409.19471/) (2024)
- [Specification Patterns for Robotic Missions](https://mlsanity.com/paper/1901.02077/) (2019)
- [GUARD: A Safe Reinforcement Learning Benchmark](https://mlsanity.com/paper/2305.13681/) (2023)
- [Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning](https://mlsanity.com/paper/2504.07095/) (2025)
- [Safety-Critical Control for Autonomous Systems: Control Barrier Functions via Reduced-Order Models](https://mlsanity.com/paper/2403.09865/) (2024)
- [STLCG++: A Masking Approach for Differentiable Signal Temporal Logic Specification](https://mlsanity.com/paper/2501.04194/) (2025)
- [Follow The Rules: Online Signal Temporal Logic Tree Search for Guided Imitation Learning in Stochastic Domains](https://mlsanity.com/paper/2209.13737/) (2022)
- [Logically Constrained Robotics Transformers for Enhanced Perception-Action Planning](https://mlsanity.com/paper/2408.05336/) (2024)
- [Safe Control of Quadruped in Varying Dynamics via Safety Index Adaptation](https://mlsanity.com/paper/2409.09882/) (2024)
- [Pretrained Embeddings as a Behavior Specification Mechanism](https://mlsanity.com/paper/2503.02012/) (2025)
- [Demonstrating ViSafe: Vision-enabled Safety for High-speed Detect and Avoid](https://mlsanity.com/paper/2505.03694/) (2025)

## Built on by (most cited first, 5 of 5)

- [Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation](https://mlsanity.com/paper/2606.05660/) (2026)
- [Specification-Aware Distribution Shaping for Robotics Foundation Models](https://mlsanity.com/paper/2603.17969/) (2026)
- [CLAMP: Constrained Decoding for Vision-Language Embodied Planning](https://mlsanity.com/paper/2609.08602/) (2026)
- [Security and Privacy in Large-Model-Driven Embodied Agents: Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2609.27847/) (2026)
- [A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies](https://mlsanity.com/paper/2610.05166/) (2026)

## Abstract (arXiv)

Recent advances in the development of robotic foundation models have led to promising end-to-end and general-purpose capabilities in robotic systems. Trained on vast datasets of simulated and real-world trajectories, these policies map multimodal observations directly to action sequences for physical execution. Despite promising real-world capabilities, these models are still data-driven and, therefore, lack explicit notions of behavioral correctness. We address this gap by introducing SafeDec, a constrained decoding framework for autoregressive, transformer-based robot navigation foundation models that enforces safety specifications expressed as Signal Temporal Logic (STL) formulas. Our method ensures that generated actions provably satisfy STL specifications under assumed dynamics at runtime without retraining while remaining agnostic of the underlying policy. We evaluate SafeDec on tasks from the CHORES benchmark for state-of-the-art embodied navigation policies across hundreds of procedurally generated environments and show that our decoding-time interventions are useful not only for filtering unsafe actions but also for conditional action generation. Videos are available at constrained-robot-fms.github.io