arXiv subjects

Hyeonwoo Lee

Publications and source records attributed to Hyeonwoo Lee.

5 recordsLinked to original sources

arXiv2026

OpenHEART: Opening Heterogeneous Articulated Objects with a Legged Manipulator

Legged manipulators offer high mobility and versatile manipulation. However, robust interaction with heterogeneous articulated objects, such as doors, drawers, and cabinets, remains challenging because of the diverse articulation types of the objects and the complex dynamics of the legged robot. Existing reinforcement learning (RL)-based approaches often rely on high-dimensional sensory inputs, leading to sample inefficiency. In this paper, we propose a robust and sample-efficient framework for opening heterogeneous articulated objects with a legged manipulator. In particular, we propose Sampling-based Abstracted Feature Extraction (SAFE), which encodes handle and panel geometry into a compact low-dimensional representation, improving cross-domain generalization. Additionally, Articulation Information Estimator (ArtIEst) is introduced to adaptively mix proprioception with exteroception to estimate opening direction and range of motion for each object. The proposed framework was deployed to manipulate various heterogeneous articulated objects in simulation and real-world robot systems. Videos can be found on the project website: https://openheart-icra.github.io/OpenHEART/

cs.RO↗

arXiv2026

DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning

Quadrupedal robots hold promising potential for applications in navigating cluttered environments with resilience akin to their animal counterparts. However, their floating base configuration makes them vulnerable to real-world uncertainties, yielding substantial challenges in their locomotion control. Deep reinforcement learning has become one of the plausible alternatives for realizing a robust locomotion controller. However, the approaches that rely solely on proprioception sacrifice collision-free locomotion because they require front-feet contact to detect the presence of stairs to adapt the locomotion gait. Meanwhile, incorporating exteroception necessitates a precisely modeled map observed by exteroceptive sensors over a period of time. Therefore, this work proposes a novel method to fuse proprioception and exteroception featuring a resilient multi-modal reinforcement learning. The proposed method yields a controller that showcases agile locomotion performance on a quadrupedal robot over a myriad of real-world courses, including rough terrains, steep slopes, and high-rise stairs, while retaining its robustness against out-of-distribution situations.

cs.RO↗

arXiv2024

TRIP: Terrain Traversability Mapping With Risk-Aware Prediction for Enhanced Online Quadrupedal Robot Navigation

Accurate traversability estimation using an online dense terrain map is crucial for safe navigation in challenging environments like construction and disaster areas. However, traversability estimation for legged robots on rough terrains faces substantial challenges owing to limited terrain information caused by restricted field-of-view, and data occlusion and sparsity. To robustly map traversable regions, we introduce terrain traversability mapping with risk-aware prediction (TRIP). TRIP reconstructs the terrain maps while predicting multi-modal traversability risks, enhancing online autonomous navigation with the following contributions. Firstly, estimating steppability in a spherical projection space allows for addressing data sparsity while accomodating scalable terrain properties. Moreover, the proposed traversability-aware Bayesian generalized kernel (T-BGK)-based inference method enhances terrain completion accuracy and efficiency. Lastly, leveraging the steppability-based Mahalanobis distance contributes to robustness against outliers and dynamic elements, ultimately yielding a static terrain traversability map. As verified in both public and our in-house datasets, our TRIP shows significant performance increases in terms of terrain reconstruction and navigation map. A demo video that demonstrates its feasibility as an integral component within an onboard online autonomous navigation system for quadruped robots is available at https://youtu.be/d7HlqAP4l0c.

cs.RO↗

arXiv2021

Quantitative in situ measurement of optical force along a strand of cleaved silica optical fiber induced by the light guided therewithin

We proposed an optomechanical system to quantify the net force on a strand of cleaved silica optical fiber in situ as the laser light was being guided through it. Four strands of the fiber were bond to both sides of a macroscopic oscillator, whose movements were accurately monitored by a Michelson interferometer. The laser light was propagating with variable optical powers and frequency modulations. Experimentally, we discovered that the driving force for the oscillator consisted of not only the optical force of the light exiting from the cleaved facets but also the tension along the fiber induced by the light guided therewithin. The net driving force was determined only by the optical power, refractive index of the fiber, and the speed of light, which pinpoints its fundamental origin.

physics.optics↗

arXiv2020

Radiation pressure measurement using a macroscopic oscillator in an ambient environment

In contrast to current efforts to quantify the radiation pressure of light using nano-micromechanical resonators in cryogenic conditions, we proposed and experimentally demonstrated the radiation pressure measurement in ambient conditions by utilizing a macroscopic mechanical longitudinal oscillator with an effective mass of the order of 20 g. The light pressure on a mirror attached to the oscillator was recorded in a Michelson interferometer and results showed, within the experimental accuracy of 3.9%, a good agreement with the harmonic oscillator model without free parameters.

physics.optics↗