Related papers: MonoForce: Self-supervised Learning of Physics-inf…
We propose end-to-end differentiable model that predicts robot trajectories on rough offroad terrain from camera images and/or lidar point clouds. The model integrates a learnable component that predicts robot-terrain interaction forces…
We present a novel monocular localization framework by jointly training deep learning-based depth prediction and Bayesian filtering-based pose reasoning. The proposed cross-modal framework significantly outperforms deep learning-only…
Uncertainty-aware robot motion prediction is crucial for downstream traversability estimation and safe autonomous navigation in unstructured, off-road environments, where terrain is heterogeneous and perceptual uncertainty is high. Most…
Moving in dynamic pedestrian environments is one of the important requirements for autonomous mobile robots. We present a model-based reinforcement learning approach for robots to navigate through crowded environments. The navigation policy…
Accurate and robust navigation in unstructured environments requires fusing data from multiple sensors. Such fusion ensures that the robot is better aware of its surroundings, including areas of the environment that are not immediately…
In many applications, robots are increasingly deployed in unstructured and natural environments where they encounter various types of vegetation. Vegetation presents unique challenges as a traversable obstacle, where the mechanical…
Navigating unknown environments with a single RGB camera is challenging, as the lack of depth information prevents reliable collision-checking. While some methods use estimated depth to build collision maps, we found that depth estimates…
Accurate traversability estimation is essential for safe and effective navigation of outdoor robots operating in complex environments. This paper introduces a novel experience-based method that allows robots to autonomously learn which…
Mobile robots should be capable of planning cost-efficient paths for autonomous navigation. Typically, the terrain and robot properties are subject to variations. For instance, properties of the terrain such as friction may vary across…
Self-supervised monocular depth estimation methods aim to be used in critical applications such as autonomous vehicles for environment analysis. To circumvent the potential imperfections of these approaches, a quantification of the…
Wheeled robots have recently demonstrated superior mechanical capability to traverse vertically challenging terrain (e.g., extremely rugged boulders comparable in size to the vehicles themselves). Negotiating such terrain introduces…
Force sensing is essential for dexterous robot manipulation, but scaling force-aware policy learning is hindered by the heterogeneity of tactile sensors. Differences in sensing principles (e.g., optical vs. magnetic), form factors, and…
We present the design of a low-cost wheeled mobile robot, and an analytical model for predicting its motion under the influence of motor torques and friction forces. Using our proposed model, we show how to analytically compute the gradient…
We present a self-supervised approach for learning to predict traversable paths for wheeled mobile robots that require good traction to navigate. Our algorithm, termed WayFAST (Waypoint Free Autonomous Systems for Traversability), uses RGB…
Deep reinforcement learning has great potential to acquire complex, adaptive behaviors for autonomous agents automatically. However, the underlying neural network polices have not been widely deployed in real-world applications, especially…
Ground robots require the crucial capability of traversing unstructured and unprepared terrains and avoiding obstacles to complete tasks in real-world robotics applications such as disaster response. When a robot operates in off-road field…
Reinforcement learning can enable complex, adaptive behavior to be learned automatically for autonomous robotic platforms. However, practical deployment of reinforcement learning methods must contend with the fact that the training process…
In autonomous navigation settings, several quantities can be subject to variations. Terrain properties such as friction coefficients may vary over time depending on the location of the robot. Also, the dynamics of the robot may change due…
Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with…
Legged robots must exhibit robust and agile locomotion across diverse, unstructured terrains, a challenge exacerbated under blind locomotion settings where terrain information is unavailable. This work introduces a hierarchical…