Adaptive Policy Switching of Two-Wheeled Differential Robots for Traversing over Diverse Terrains

• URL: http://arxiv.org/abs/2603.04761v1
• Date: Thu, 05 Mar 2026 03:20:06 GMT
• Title: Adaptive Policy Switching of Two-Wheeled Differential Robots for Traversing over Diverse Terrains
• Abstract summary: This study investigates whether terrain types can be estimated effectively using posture-related observations collected during navigation.<n>We fine-tuned a pre-trained policy using Proximal Policy Optimization (PPO), and then collected the robot's 3D orientation data as it moved across flat and rough terrain.<n>Our analysis revealed that the standard deviation of the robot's pitch data shows a clear difference between these two terrain types.
• Score: 1.9573380763700712
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Exploring lunar lava tubes requires robots to traverse without human intervention. Because pre-trained policies cannot fully cover all possible terrain conditions, our goal is to enable adaptive policy switching, where the robot selects an appropriate terrain-specialized model based on its current terrain features. This study investigates whether terrain types can be estimated effectively using posture-related observations collected during navigation. We fine-tuned a pre-trained policy using Proximal Policy Optimization (PPO), and then collected the robot's 3D orientation data as it moved across flat and rough terrain in a simulated lava-tube environment. Our analysis revealed that the standard deviation of the robot's pitch data shows a clear difference between these two terrain types. Using Gaussian mixture models (GMM), we evaluated terrain classification across various window sizes. An accuracy of more than 98% was achieved when using a 70-step window. The result suggests that short-term orientation data are sufficient for reliable terrain estimation, providing a foundation for adaptive policy switching.

Related papers

• Meridian: Metric-Semantic Primitive Matching for Cross-View Geo-Localization Beyond Urban Environments [47.53030013880309]
  Successful robot automation requires accurate global localization to support repeatability, task planning, goal specification, and safe operation.<n>We present Meridian, a method for matching high-level metric-semantic primitives across aerial images and ground robot RGB-D camera data.<n>We demonstrate that our algorithm can localize a ground robot across a wide variety of environments, including an autonomous driving dataset, a park and campus area, and a wilderness camp.
  arXiv  Detail & Related papers  (2026-06-04T15:52:40Z)
• Bridging Simulation and Reality: Cross-Domain Transfer with Semantic 2D Gaussian Splatting [60.513168855890974]
  Cross-domain transfer in robotic manipulation is a longstanding challenge due to the significant domain gap between simulated and real-world environments.<n>We propose Semantic 2D Gaussian Splatting (S2GS), a novel representation method that extracts object-centric, domain-invariant spatial features.<n>S2GS significantly improves sim-to-real transferability, maintaining high and stable task performance in real-world scenarios.
  arXiv  Detail & Related papers  (2025-12-04T12:16:15Z)
• Adaptive path planning for efficient object search by UAVs in agricultural fields [0.0]
  This paper presents an adaptive path planner for object search in agricultural fields using UAVs.<n>The planner uses a high-altitude coverage flight path and plans additional low-altitude inspections when the detection network is uncertain.<n>We trained a YOLOv8 detection network to detect artificial plants placed in grass fields to showcase the potential of our path planner.
  arXiv  Detail & Related papers  (2025-04-03T10:47:31Z)
• NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration [57.15811390835294]
  This paper describes how we can train a single unified diffusion policy to handle both goal-directed navigation and goal-agnostic exploration. We show that this unified policy results in better overall performance when navigating to visually indicated goals in novel environments. Our experiments, conducted on a real-world mobile robot platform, show effective navigation in unseen environments in comparison with five alternative methods.
  arXiv  Detail & Related papers  (2023-10-11T21:07:14Z)
• Wait, That Feels Familiar: Learning to Extrapolate Human Preferences for Preference Aligned Path Planning [46.66453816117135]
  Preference extrApolation for Terrain awarE Robot Navigation, PATERN, is a novel framework for extrapolating operator terrain preferences for visual navigation. We show PATERN robustly generalizes to diverse terrains and varied lighting conditions, while navigating in a preference aligned manner.
  arXiv  Detail & Related papers  (2023-09-18T16:24:26Z)
• VAPOR: Legged Robot Navigation in Outdoor Vegetation Using Offline Reinforcement Learning [53.13393315664145]
  We present VAPOR, a novel method for autonomous legged robot navigation in unstructured, densely vegetated outdoor environments. Our method trains a novel RL policy using an actor-critic network and arbitrary data collected in real outdoor vegetation. We observe that VAPOR's actions improve success rates by up to 40%, decrease the average current consumption by up to 2.9%, and decrease the normalized trajectory length by up to 11.2%.
  arXiv  Detail & Related papers  (2023-09-14T16:21:27Z)
• Robust Visual Sim-to-Real Transfer for Robotic Manipulation [79.66851068682779]
  Learning visuomotor policies in simulation is much safer and cheaper than in the real world. However, due to discrepancies between the simulated and real data, simulator-trained policies often fail when transferred to real robots. One common approach to bridge the visual sim-to-real domain gap is domain randomization (DR)
  arXiv  Detail & Related papers  (2023-07-28T05:47:24Z)
• Learning multiobjective rough terrain traversability [0.0]
  We present a method that uses high-resolution topography data of rough terrain, and ground vehicle simulation, to predict traversability. A deep neural network is trained to predict the traversability measures from the local heightmap and target speed. We evaluate the model on laser-scanned forest terrains, previously unseen by the model.
  arXiv  Detail & Related papers  (2022-03-30T14:31:43Z)
• Learning Continuous Environment Fields via Implicit Functions [144.4913852552954]
  We propose a novel scene representation that encodes reaching distance -- the distance between any position in the scene to a goal along a feasible trajectory. We demonstrate that this environment field representation can directly guide the dynamic behaviors of agents in 2D mazes or 3D indoor scenes.
  arXiv  Detail & Related papers  (2021-11-27T22:36:58Z)
• Complex Terrain Navigation via Model Error Prediction [5.937673383513695]
  We train with an on-policy approach, resulting in successful navigation policies using as little as 50 minutes of training data split across simulation and real world. Our learning-based navigation system is a sample efficient short-term planner that we demonstrate on a Clearpath Husky navigating through a variety of terrain.
  arXiv  Detail & Related papers  (2021-11-18T15:55:04Z)
• Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning [75.56839075060819]
  Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state. reinforcement learning approaches can operate directly from raw sensory inputs with only a reward signal to describe the task, but are extremely sample-inefficient and brittle. In this work, we combine the strengths of model-based methods with the flexibility of learning-based methods to obtain a general method that is able to overcome inaccuracies in the robotics perception/actuation pipeline.
  arXiv  Detail & Related papers  (2020-05-21T19:47:05Z)

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.