Learning to Walk Fast: Optimized Hip Height Movement for Simulated and Real Humanoid Robots

Shafii, Nima; Lau, Nuno; Reis, Luís Paulo

doi:10.1007/s10846-015-0191-5

Cited by 17 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous groundwork has obtained methodologies for several types of kicks (long, quick, precise). Nevertheless the current implementation still does not allow the kicks to be performed in a similar way to humans, that is, without stopping their forward motion [9,10,11].…”

Section: Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Humanoid Robot Kick in Motion Ability for Playing Robotic Soccer

Teixeira

Silva

Abreu

et al. 2020

2020 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

Self Cite

View full text Add to dashboard Cite

Robotics and Artificial Intelligence are two deeply intertwined fields of study, currently experiencing formidable growth. To foster these developments, the RoboCup initiative is a fantastic test bed to experiment new approaches and ideas. This dissertation is rooted in the groundwork laid by previous FCPortugal3D contributions for the RoboCup simulation 3D robotic soccer league, and seeks to design and implement a humanoid robotic kick system for situations where the robot is moving. It employs Reinforcement Learning (RL) techniques, namely the Proximal Policy Optimization (PPO) algorithm to create fast and reliable skills. The kick was divided into 6 cases according to initial conditions and separately trained for each of the cases. A series of kicks, both static and in motion, using two different gaits were developed. The kicks obtained show very high reliability and, when compared to state of the art kicks, displayed a very high time performance improvement. This opens the door to more dynamic games with faster kicks in the RoboCup simulation 3D league.

show abstract

Section: Motivationmentioning

confidence: 99%

“…Nevertheless, several relevant documents relating to both the FCPortugal3D team, some already widely cited in this document, and others such as [66,67,68,69,70,71,72,73] were studied in order to understand the current existing capabilities and approaches taken by members of the team.…”

Section: Previous Work In Robocupmentioning

confidence: 99%

Humanoid Robot Kick in Motion Ability for Playing Robotic Soccer

Teixeira

Silva

Abreu

et al. 2020

2020 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although ES methods have an even lower sample efficiency than RL methods, ES methods are computationally efficient and have better exploration characteristics, which can provide robustness in robot training. Accordingly, a covariance matrix adaptation evolution strategy (CMA-ES) [38], which is one of the state-of-the-art ES methods, has been applied to robot tasks, such as the locomotion of humanoid [39] and quadruped [40] robots.…”

Section: Training Of Autonomous Robotsmentioning

confidence: 99%

Sample-Efficient Training of Robotic Guide Using Human Path Prediction Network

Moon

Seo²

2020

Preprint

View full text Add to dashboard Cite

Training a robot that engages with people is challenging, because it is expensive to involve people in a robot training process requiring numerous data samples. This paper proposes a human path prediction network (HPPN) and an evolution strategy-based robot training method using virtual human movements generated by the HPPN, which compensates for this sample inefficiency problem. We applied the proposed method to the training of a robotic guide for visually impaired people, which was designed to collect multimodal human response data and reflect such data when selecting the robot's actions. We collected 1,507 real-world episodes for training the HPPN and then generated over 100,000 virtual episodes for training the robot policy. User test results indicate that our trained robot accurately guides blindfolded participants along a goal path. In addition, by the designed reward to pursue both guidance accuracy and human comfort during the robot policy training process, our robot leads to improved smoothness in human motion while maintaining the accuracy of the guidance. This sample-efficient training method is expected to be widely applicable to all robots and computing machinery that physically interact with humans.

show abstract

“…Shafii et al utilized central pattern generators to modulate generated bipedal walking trajectories with varying hip height [41]. Covariance matrix adaptation evolution strategy enabled the robot controller to search for feasible hip height patterns and walking parameters in a way to optimize forward velocity.…”

Section: Related Work To Robot Trajectory Representationsmentioning

confidence: 99%

Learning to exploit passive compliance for energy-efficient gait generation on a compliant humanoid

et al. 2018

View full text Add to dashboard Cite

Modern humanoid robots include not only active compliance but also passive compliance. Apart from improved safety and dependability, availability of passive elements, such as springs, opens up new possibilities for improving the energy efficiency.With this in mind, this paper addresses the challenging open problem of exploiting the passive compliance for the purpose of energy efficient humanoid walking. To this end, we develop a method comprising two parts: An optimization part that finds an optimal vertical center-of-mass trajectory, and a walking pattern generator part that uses this trajectory to produce a dynamically-balanced gait. For the optimization part, we propose a reinforcement learning approach that dynamically evolves the policy parametrization during the learning process. By gradually increasing the representational power of the policy parametrization, it manages to find better policies in a faster and computationally efficient way. For the walking generator part, we develop a variable-centerof-mass-height ZMP-based bipedal walking pattern generator. The method is tested in real-world experiments with the bipedal robot COMAN and achieves a significant 18% reduction in the electric energy consumption

show abstract

Learning to Walk Fast: Optimized Hip Height Movement for Simulated and Real Humanoid Robots

Cited by 17 publications

References 18 publications

Humanoid Robot Kick in Motion Ability for Playing Robotic Soccer

Humanoid Robot Kick in Motion Ability for Playing Robotic Soccer

Sample-Efficient Training of Robotic Guide Using Human Path Prediction Network

Learning to exploit passive compliance for energy-efficient gait generation on a compliant humanoid

Contact Info

Product

Resources

About