Kuan-Yu Tseng — accepted AI-conference papers

2024

Adaptive Trajectory Database Learning for Nonlinear Control with Hybrid Gradient Optimization

Kuan-Yu Tseng, Mengchao Zhang, Kris Hauser, Geir E. Dullerud

IROS 2024poster

This paper presents a novel experience-based technique, called EHGO, for sample-efficient adaptive control of nonlinear systems in the presence of dynamical modeling errors. The starting point for EHGO is a database seeded with many trajectories optimized under a reference estimate of real system dy…

Cited by 0 Source ↗Scholar ↗

2020

Development of a Running Hexapod Robot with Differentiated Front and Hind Leg Morphology and Functionality

Jia-Ruei Chiu, Yu-Chih Huang, Hui-Ching Chen, Kuan-Yu Tseng, Pei-Chun Lin

IROS 2020poster

This article introduces an innovative model-based strategy for designing a legged robot to generate animal-like running dynamics with differentiated leg braking and thrusting force patterns. Linear springs were utilized as legs, but instead of having one end of each spring connected directly to the…

Cited by 2 Source ↗Scholar ↗