mlsanityData to 14 Oct 2026

Towards Safe Path Tracking Using the Simplex Architecture

arXiv 2503.10559 ↗First posted 13 Mar 2025cs.ROcited by 0

On the map: Deep reinforcement learning methods → Safe and constrained RL

Abstract (arXiv)

Robot navigation in complex environments necessitates controllers that prioritize safety while remaining performant and adaptable. Traditional controllers like Regulated Pure Pursuit, Dynamic Window Approach, and Model-Predictive Path Integral, while reliable, struggle to adapt to dynamic conditions. Reinforcement Learning offers adaptability but state-wise safety guarantees remain challenging and often absent in practice. To address this, we propose a path tracking controller leveraging the Simplex architecture. It combines a Reinforcement Learning controller for adaptiveness and performance with a high-assurance controller providing safety and stability. Our main goal is to provide a safe testbed for the design and evaluation of path-planning algorithms, including machine-learning-based planners. Our contribution is twofold. We firstly discuss general stability and safety considerations for designing controllers using the Simplex architecture. Secondly, we present a Simplex-based path tracking controller. Our simulation results, supported by preliminary in-field tests, demonstrate the controller's effectiveness in maintaining safety while achieving comparable performance to state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 31 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

10 of 31 references.

References · 10

  1. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 899
  2. 2022Robot Operating System 2: Design, Architecture, and Uses In The Wildcited by 199
  3. 2020The Marathon 2: A Navigation Systemcited by 70
  4. 2023From the Desks of ROS Maintainers: A Survey of Modern & Capable Mobile Robotics Algorithms in the Robot Operating System 2cited by 11
  5. 2023Regulated Pure Pursuit for Robot Path Trackingcited by 8
  6. 2023Towards Efficient MPPI Trajectory Generation with Unscented Guidance: U-MPPI Control Strategycited by 5
  7. 2025DualGuard MPPI: Safe and Performant Optimal Control by Combining Sampling-Based MPC and Hamilton-Jacobi Reachabilitycited by 4
  8. 2015Switching control for incremental stabilization of nonlinear systems via contraction theorycited by 1
  9. 2021Safety Embedded Control of Nonlinear Systems via Barrier Statescited by 1
  10. 2021Necessary and Sufficient Conditions for Stability of Discrete-Time Switched Linear Systems with Ranged Dwell Timecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Tasks
  2. 2021Runtime Safety Assurance for Learning-enabled Control of Autonomous Driving Vehicles
  3. 2025Safe Reinforcement Learning with a Predictive Safety Filter for Motion Planning and Control: A Drifting Vehicle Example
  4. 2025Platform-Agnostic Reinforcement Learning Framework for Safe Exploration of Cluttered Environments with Graph Attention
  5. 2025From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policies
  6. 2025SafeMove-RL: A Certifiable Reinforcement Learning Framework for Dynamic Motion Constraints in Trajectory Planning
  7. 2025Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation
  8. 2026DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles