Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments

• URL: http://arxiv.org/abs/2605.28442v2
• Date: Fri, 29 May 2026 08:52:05 GMT
• Title: Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments
• Abstract summary: Self-supervised online traversability estimation enables robots to continuously learn from unlabeled open-world experiences.<n>We introduce COTRATE, an online learning framework for continuous traversability estimation from multimodal, unlabeled robot experience.
• Score: 14.96664579110115
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised online traversability estimation enables robots to continuously learn from unlabeled open-world experiences and adapt their navigation behavior toward safe and efficient trajectories. Existing approaches either rely on handcrafted proprioceptive traversability scores, limiting robot-agnosticism, or cluster prior data, preventing online learning. Moreover, many continual learning methods incur substantial memory and computational costs, hindering onboard deployment. We introduce COTRATE, an online learning framework for continuous traversability estimation from multimodal, unlabeled robot experience. Our method first infers robust traversability scores using a robot-agnostic, learning-based online terrain assessment module operating on proprioceptiveand inertial signals. These scores then supervise a visual traversability network through a novel alignment loss that associates visual embeddings with online terrain assessments. To mitigate forgetting during continual learning with minimal overhead, we propose a diversity-aware feature selection strategythat preserves performance using a compact replay memory. We further show that the learned traversability representation supports knowledge transfer across different robot platforms with different locomotion kinematics. We evaluate COTRATE on a dataset of $\approx$ 50,000 images collected with two robotic platforms across 11 outdoor terrains, and benchmark it on navigation tasks in three representative outdoor environments. We make the dataset, code, and trained models publicly available.

Related papers

• Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning [58.3994826169858]
  We introduce RoboFuME, a reset-free fine-tuning system for robotic reinforcement learning. Our insights are to utilize offline reinforcement learning techniques to ensure efficient online fine-tuning of a pre-trained policy. Our method can incorporate data from an existing robot dataset and improve on a target task within as little as 3 hours of autonomous real-world experience.
  arXiv  Detail & Related papers  (2023-10-23T17:50:08Z)
• STERLING: Self-Supervised Terrain Representation Learning from Unconstrained Robot Experience [43.49602846732077]
  We introduce Self-supervised TErrain Representation LearnING (STERLING) STERLING is a novel approach for learning terrain representations that relies solely on easy-to-collect, unconstrained (e.g., non-expert) and unlabelled robot experience. We evaluate STERLING features on the task of preference-aligned visual navigation and find that STERLING features perform on par with fully supervised approaches.
  arXiv  Detail & Related papers  (2023-09-26T22:55:32Z)
• Offline Reinforcement Learning for Visual Navigation [66.88830049694457]
  ReViND is the first offline RL system for robotic navigation that can leverage previously collected data to optimize user-specified reward functions in the real-world. We show that ReViND can navigate to distant goals using only offline training from this dataset, and exhibit behaviors that qualitatively differ based on the user-specified reward function.
  arXiv  Detail & Related papers  (2022-12-16T02:23:50Z)
• GNM: A General Navigation Model to Drive Any Robot [67.40225397212717]
  General goal-conditioned model for vision-based navigation can be trained on data obtained from many distinct but structurally similar robots. We analyze the necessary design decisions for effective data sharing across robots. We deploy the trained GNM on a range of new robots, including an under quadrotor.
  arXiv  Detail & Related papers  (2022-10-07T07:26:41Z)
• WayFAST: Traversability Predictive Navigation for Field Robots [5.914664791853234]
  We present a self-supervised approach for learning to predict traversable paths for wheeled mobile robots. Our key inspiration is that traction can be estimated for rolling robots using kinodynamic models. We show that our training pipeline based on online traction estimates is more data-efficient than other-based methods.
  arXiv  Detail & Related papers  (2022-03-22T22:02:03Z)
• Unsupervised Online Learning for Robotic Interestingness with Visual Memory [9.189959184116962]
  We develop a method that automatically adapts online to the environment to report interesting scenes quickly. We achieve an average of 20% higher accuracy than the state-of-the-art unsupervised methods in a subterranean tunnel environment.
  arXiv  Detail & Related papers  (2021-11-18T16:51:39Z)
• Learning Perceptual Locomotion on Uneven Terrains using Sparse Visual Observations [75.60524561611008]
  This work aims to exploit the use of sparse visual observations to achieve perceptual locomotion over a range of commonly seen bumps, ramps, and stairs in human-centred environments. We first formulate the selection of minimal visual input that can represent the uneven surfaces of interest, and propose a learning framework that integrates such exteroceptive and proprioceptive data. We validate the learned policy in tasks that require omnidirectional walking over flat ground and forward locomotion over terrains with obstacles, showing a high success rate.
  arXiv  Detail & Related papers  (2021-09-28T20:25:10Z)
• Rapid Exploration for Open-World Navigation with Latent Goal Models [78.45339342966196]
  We describe a robotic learning system for autonomous exploration and navigation in diverse, open-world environments. At the core of our method is a learned latent variable model of distances and actions, along with a non-parametric topological memory of images. We use an information bottleneck to regularize the learned policy, giving us (i) a compact visual representation of goals, (ii) improved generalization capabilities, and (iii) a mechanism for sampling feasible goals for exploration.
  arXiv  Detail & Related papers  (2021-04-12T23:14:41Z)
• ViNG: Learning Open-World Navigation with Visual Goals [82.84193221280216]
  We propose a learning-based navigation system for reaching visually indicated goals. We show that our system, which we call ViNG, outperforms previously-proposed methods for goal-conditioned reinforcement learning. We demonstrate ViNG on a number of real-world applications, such as last-mile delivery and warehouse inspection.
  arXiv  Detail & Related papers  (2020-12-17T18:22:32Z)
• NavRep: Unsupervised Representations for Reinforcement Learning of Robot Navigation in Dynamic Human Environments [28.530962677406627]
  We train two end-to-end, and 18 unsupervised-learning-based architectures, and compare them, along with existing approaches, in unseen test cases. Our results show that unsupervised learning methods are competitive with end-to-end methods. This release also includes OpenAI-gym-compatible environments designed to emulate the training conditions described by other papers.
  arXiv  Detail & Related papers  (2020-12-08T12:51:14Z)
• Robot Perception enables Complex Navigation Behavior via Self-Supervised Learning [23.54696982881734]
  We propose an approach to unify successful robot perception systems for active target-driven navigation tasks via reinforcement learning (RL) Our method temporally incorporates compact motion and visual perception data, directly obtained using self-supervision from a single image sequence. We demonstrate our approach on two real-world driving dataset, KITTI and Oxford RobotCar, using the new interactive CityLearn framework.
  arXiv  Detail & Related papers  (2020-06-16T07:45:47Z)

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.