Neural fidelity warping for efficient robot morphology design

Hu, Sha; Yang, Zeshi; Mori, Greg

doi:10.1109/icra48506.2021.9561733

Cited by 3 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An acquisition function is applied to query the most promising and informative regions based on current estimations. Recently BO has seen more and more adoptions in robotics and computer graphics for various applications [Brochu et al 2010[Brochu et al , 2007Hu et al 2021;Koyama et al 2020]. Most relevant to our work, BO has been employed to tune parameters of a bipedal locomotion controller [Rai et al 2018], optimize hyperparameters of physics-based character animation systems , and discover diverse athletic jumping strategies ].…”

Section: Bayesian Optimizationmentioning

confidence: 99%

Learning to Use Chopsticks in Diverse Styles

Yang¹,

Yin²,

Liu³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Bayesian Optimizationmentioning

confidence: 99%

Learning to Use Chopsticks in Diverse Styles

Yang¹,

Yin²,

Liu³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Surrogate-Assisted Morphology Optimization by Genetic Algorithms

Jiang,

Chen,

Pei

et al. 2023

2023 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

Learning to use chopsticks in diverse gripping styles

2022

View full text Add to dashboard Cite

Learning dexterous manipulation skills is a long-standing challenge in computer graphics and robotics, especially when the task involves complex and delicate interactions between the hands, tools and objects. In this paper, we focus on chopsticks-based object relocation tasks, which are common yet demanding. The key to successful chopsticks skills is steady gripping of the sticks that also supports delicate maneuvers. We automatically discover physically valid chopsticks holding poses by Bayesian Optimization (BO) and Deep Reinforcement Learning (DRL), which works for multiple gripping styles and hand morphologies without the need of example data. Given as input the discovered gripping poses and desired objects to be moved, we build physics-based hand controllers to accomplish relocation tasks in two stages. First, kinematic trajectories are synthesized for the chopsticks and hand in a motion planning stage. The key components of our motion planner include a grasping model to select suitable chopsticks configurations for grasping the object, and a trajectory optimization module to generate collision-free chopsticks trajectories. Then we train physics-based hand controllers through DRL again to track the desired kinematic trajectories produced by the motion planner. We demonstrate the capabilities of our framework by relocating objects of various shapes and sizes, in diverse gripping styles and holding positions for multiple hand morphologies. Our system achieves faster learning speed and better control robustness, when compared to vanilla systems that attempt to learn chopstick-based skills without a gripping pose optimization module and/or without a kinematic motion planner. Our code and models are available at this link. 1

show abstract

Neural fidelity warping for efficient robot morphology design

Cited by 3 publications

References 37 publications

Learning to Use Chopsticks in Diverse Styles

Learning to Use Chopsticks in Diverse Styles

Surrogate-Assisted Morphology Optimization by Genetic Algorithms

Learning to use chopsticks in diverse gripping styles

Contact Info

Product

Resources

About