← Search

Arthicha Srisuchinnawong

4 accepted papers

2025

Gain Tuning Is Not What You Need: Reward Gain Adaptation for Constrained Locomotion Learning

RSS 2025poster

Existing robot locomotion learning techniques rely heavily on the offline selection of proper reward weighting gains and cannot guarantee constraint satisfaction (i.e., constraint violation) during training. Thus, this work aims to address both issues by proposing Reward-Oriented Gains via Embodied…

Cited by 0PDFScholar
2024

Unsupervised Multiple Proactive Behavior Learning of Mobile Robots for Smooth and Safe Navigation

IROS 2024poster

While different control approaches have been developed for smooth and safe navigation, they are limited by the needs for model-based assumptions, true training target/reward function, and/or large sample data. To overcome these limitations, this study proposes a model-free neural control architectur…

Cited by 0SourceScholar
2022

GRAB: GRAdient-Based Shape-Adaptive Locomotion Control

RA-L 2022

Adaptive systems enable legged robots to cope with a wide range of environmental settings and unforeseen events. Existing reactive methods adapt either the walking frequency or the amplitude to only simple perturbations. This letter proposes an adaptive mechanism for central pattern generator (CPG)-

Cited by 1SourceScholar