Worasuchad Haomachai — accepted AI-conference papers

2025

Bio-Inspired Plastic Neural Networks for Zero-Shot Out-of-Distribution Generalization in Complex Animal-Inspired Robots

Binggwong Leung, Worasuchad Haomachai, Joachim Winther Pedersen, Sebastian Risi, Poramate Manoonpong

IROS 2025

Artificial neural networks can be used to solve a variety of robotic tasks. However, they risk failing catastrophically when faced with out-of-distribution (OOD) situations. Several approaches have employed a type of synaptic plasticity known as Hebbian learning that can dynamically adjust weights b

Cited by 2 Source ↗Scholar ↗

2024

Transition Gradient From Standing to Traveling Waves for Energy-Efficient Slope Climbing of a Gecko-Inspired Robot

Worasuchad Haomachai, Zhendong Dai, Poramate Manoonpong

RA-L 2024

Lateral undulation patterns of a flexible spine, including standing waves, traveling waves, and their transitions, enable agile and versatile locomotion in sprawling animals. Inspired by this, we proposed body-wave transition strategies for energy-efficient inclined-surface climbing of a gecko-inspi

Cited by 7 Source ↗Scholar ↗

2021

Lateral Undulation of the Bendable Body of a Gecko-Inspired Robot for Energy-Efficient Inclined Surface Climbing

Worasuchad Haomachai, Donghao Shao, Wei Wang, Aihong Ji, Zhendong Dai, Poramate Manoonpong

RA-L 2021

Sprawling posture animals with their bendable spine, such as salamanders, and geckos, can perform agile and versatile locomotion including walking, swimming, and climbing. Therefore, several roboticists have used them as templates for robot designs to investigate and generate efficient locomotion. T

Cited by 40 Source ↗Scholar ↗