REASAN: Learning Reactive Safe Navigation for Legged Robots

• URL: http://arxiv.org/abs/2512.09537v1
• Date: Wed, 10 Dec 2025 11:23:32 GMT
• Title: REASAN: Learning Reactive Safe Navigation for Legged Robots
• Abstract summary: We present a novel modularized end-to-end framework for legged reactive navigation in complex dynamic environments.<n>The system comprises four simulation-trained modules: three reinforcement-learning (RL) policies for locomotion, safety shielding, and navigation, and a transformer-based exteroceptive estimator.<n>The resulting reactive safe navigation (REASAN) system achieves fully onboard and real-time reactive navigation across both single- and multi-robot settings.
• Score: 3.0268879088436496
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a novel modularized end-to-end framework for legged reactive navigation in complex dynamic environments using a single light detection and ranging (LiDAR) sensor. The system comprises four simulation-trained modules: three reinforcement-learning (RL) policies for locomotion, safety shielding, and navigation, and a transformer-based exteroceptive estimator that processes raw point-cloud inputs. This modular decomposition of complex legged motor-control tasks enables lightweight neural networks with simple architectures, trained using standard RL practices with targeted reward shaping and curriculum design, without reliance on heuristics or sophisticated policy-switching mechanisms. We conduct comprehensive ablations to validate our design choices and demonstrate improved robustness compared to existing approaches in challenging navigation tasks. The resulting reactive safe navigation (REASAN) system achieves fully onboard and real-time reactive navigation across both single- and multi-robot settings in complex environments. We release our training and deployment code at https://github.com/ASIG-X/REASAN.

Related papers

• Current state of the multi-agent multi-view experimental and digital twin rendezvous (MMEDR-Autonomous) framework [0.0]
  Machine learning-based methods can be integrated within the guidance, navigation, and control architecture to design a robust rendezvous and docking framework.<n>MMEDR-Autonomous is a unified framework comprising a learning-based optical navigation network, a reinforcement learning-based guidance approach under ongoing development, and a hardware-in-the-loop testbed.<n>The MMEDR-Autonomous framework is currently progressing toward integrated experimental validation in multi-agent rendezvous scenarios.
  arXiv  Detail & Related papers  (2026-03-21T00:13:54Z)
• CLASH: Collaborative Large-Small Hierarchical Framework for Continuous Vision-and-Language Navigation [38.37757288365413]
  Vision-and-Language Navigation (VLN) requires robots to follow natural language instructions and navigate complex environments without prior maps.<n>We propose CLASH, a VLN-CE framework that integrates a reactive small-model planner (RSMP) with a reflective large-model reasoner (RLMR)<n>In simulation, we replace the rule-based controller with a fully learnable point-goal policy, and in real-world deployment, we design a LiDAR-based clustering module for generating navigable waypoints.
  arXiv  Detail & Related papers  (2025-12-11T07:20:06Z)
• Hierarchical Decision-Making for Autonomous Navigation: Integrating Deep Reinforcement Learning and Fuzzy Logic in Four-Wheel Independent Steering and Driving Systems [19.641592340569577]
  This paper presents a hierarchical decision-making framework for autonomous navigation in 4WISD systems.<n>The proposed approach integrates deep reinforcement learning for high-level navigation with fuzzy logic for low-level control to ensure both task performance and physical feasibility.
  arXiv  Detail & Related papers  (2025-08-22T17:57:56Z)
• From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning [59.88543114325153]
  We introduce the Seeing-to-Experiencing framework to scale the capability of navigation foundation models with reinforcement learning.<n>S2E combines the strengths of pre-training on videos and post-training through RL.<n>We establish a comprehensive end-to-end evaluation benchmark, NavBench-GS, built on photorealistic 3DGS reconstructions of real-world scenes.
  arXiv  Detail & Related papers  (2025-07-29T17:26:10Z)
• RoboRAN: A Unified Robotics Framework for Reinforcement Learning-Based Autonomous Navigation [15.548637925166986]
  We present a multi-domain framework for training, evaluating and deploying RL-based navigation policies across diverse robotic platforms and operational environments.<n>Our work presents four key contributions: (1) a scalable and modular framework, facilitating seamless robot-task interchangeability and reproducible training pipelines; (2) sim-to-real transfer demonstrated through real-world experiments with multiple robots; and (3) the release of the first open-source API for deploying Isaac Lab-trained policies to real robots.
  arXiv  Detail & Related papers  (2025-05-20T15:48:23Z)
• Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation [55.02966123945644]
  We propose a hierarchical control framework leveraging neural network verification techniques to design control barrier functions (CBFs) and policy correction mechanisms.<n>Our approach relies on probabilistic enumeration to identify unsafe regions of operation, which are then used to construct a safe CBF-based control layer.<n>These experiments demonstrate the ability of the proposed solution to correct unsafe actions while preserving efficient navigation behavior.
  arXiv  Detail & Related papers  (2025-04-30T13:47:25Z)
• Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks [93.38375271826202]
  We present a method to improve generalization and robustness to distribution shifts in sim-to-real visual quadrotor navigation tasks. We first build a simulator by integrating Gaussian splatting with quadrotor flight dynamics, and then, train robust navigation policies using Liquid neural networks. In this way, we obtain a full-stack imitation learning protocol that combines advances in 3D Gaussian splatting radiance field rendering, programming of expert demonstration training data, and the task understanding capabilities of Liquid networks.
  arXiv  Detail & Related papers  (2024-06-21T13:48:37Z)
• Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning [53.3760591018817]
  We propose a new benchmarking environment for aquatic navigation using recent advances in the integration between game engines and Deep Reinforcement Learning. Specifically, we focus on PPO, one of the most widely accepted algorithms, and we propose advanced training techniques. Our empirical evaluation shows that a well-designed combination of these ingredients can achieve promising results.
  arXiv  Detail & Related papers  (2024-05-30T23:20:23Z)
• Modular Neural Network Policies for Learning In-Flight Object Catching with a Robot Hand-Arm System [55.94648383147838]
  We present a modular framework designed to enable a robot hand-arm system to learn how to catch flying objects. Our framework consists of five core modules: (i) an object state estimator that learns object trajectory prediction, (ii) a catching pose quality network that learns to score and rank object poses for catching, (iii) a reaching control policy trained to move the robot hand to pre-catch poses, and (iv) a grasping control policy trained to perform soft catching motions. We conduct extensive evaluations of our framework in simulation for each module and the integrated system, to demonstrate high success rates of in-flight
  arXiv  Detail & Related papers  (2023-12-21T16:20:12Z)
• PIC4rl-gym: a ROS2 modular framework for Robots Autonomous Navigation with Deep Reinforcement Learning [0.4588028371034407]
  This work introduces the textitPIC4rl-gym, a fundamental modular framework to enhance navigation and learning research. The paper describes the whole structure of the PIC4rl-gym, which fully integrates DRL agent's training and testing in several indoor and outdoor navigation scenarios. A modular approach is adopted to easily customize the simulation by selecting new platforms, sensors, or models.
  arXiv  Detail & Related papers  (2022-11-19T14:58:57Z)
• Efficient and Robust LiDAR-Based End-to-End Navigation [132.52661670308606]
  We present an efficient and robust LiDAR-based end-to-end navigation framework. We propose Fast-LiDARNet that is based on sparse convolution kernel optimization and hardware-aware model design. We then propose Hybrid Evidential Fusion that directly estimates the uncertainty of the prediction from only a single forward pass.
  arXiv  Detail & Related papers  (2021-05-20T17:52:37Z)
• Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments [20.017277077448924]
  NavACL is a method of automatic curriculum learning tailored to the navigation task. Deep reinforcement learning agents trained using NavACL significantly outperform state-of-the-art agents trained with uniform sampling. Our agents can navigate through unknown cluttered indoor environments to semantically-specified targets using only RGB images.
  arXiv  Detail & Related papers  (2020-09-11T13:28:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.