Task-specific Self-body Controller Acquisition by Musculoskeletal Humanoids: Application to Pedal Control in Autonomous Driving

Kawaharazuka, Kento; Tsuzuki, K.; Makino, Shogo; Onitsuka, Moritaka; Shinjo, Koki; Asano, Yuki; Okada, Kei; Kawasaki, Koji; Inaba, Masayuki

doi:10.1109/iros40897.2019.8967910

Cited by 9 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, MRC gradually makes antagonist muscles elongate and internal force Figure 6. The respective components of autonomous driving using the developed software: (a) the steering wheel operation experiment using the online learning of static module [14], (b) the pedal operation experiment using the trained dynamic module [15], (c) the steering wheel operation experiment with and without MRC [16], and (d) visual recognition of traffic lights and a human and sound recognition of a car horn.…”

Section: Application Of the Software To Autonomous Drivingmentioning

confidence: 99%

“…Also, by using this network h static , not only control but also estimation of joint angles θ est are enabled by using Extended Kalman Filter (EKF) and the change in muscle length and tension. The dynamic module (b) acquires the function h dynamic below [15],…”

Section: B Software Detailsmentioning

confidence: 99%

“…The experimental setup of autonomous driving by the musculoskeletal humanoid Musashi: the (a) pedal operation configuration, (b) experimental environment, (c) experimental configuration in the COMS[15], and (d) configuration of the PCs.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Toward Autonomous Driving by Musculoskeletal Humanoids: A Study of Developed Hardware and Learning-Based Software

Kawaharazuka

Tsuzuki

Koga

et al. 2020

IEEE Robot. Automat. Mag.

Self Cite

View full text Add to dashboard Cite

This paper summarizes an autonomous driving project by musculoskeletal humanoids. The musculoskeletal humanoid, which mimics the human body in detail, has redundant sensors and a flexible body structure. These characteristics are suitable for motions with complex environmental contact, and the robot is expected to sit down on the car seat, step on the acceleration and brake pedals, and operate the steering wheel by both arms. We reconsider the developed hardware and software of the musculoskeletal humanoid Musashi in the context of autonomous driving. The respective components of autonomous driving are conducted using the benefits of the hardware and software. Finally, Musashi succeeded in the pedal and steering wheel operations with recognition.

show abstract

Section: Application Of the Software To Autonomous Drivingmentioning

confidence: 99%

Section: B Software Detailsmentioning

confidence: 99%

See 1 more Smart Citation

Toward Autonomous Driving by Musculoskeletal Humanoids: A Study of Developed Hardware and Learning-Based Software

Kawaharazuka

Tsuzuki

Koga

et al. 2020

IEEE Robot. Automat. Mag.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this study, for stable tool-use by flexible hands, we propose a feedback control to keep the initial contact state by training the predictive model of sensor state transition expressed by a neural network. On the basis of previous studies [23], [24], we explore random search behavior, loss function, and optimization method, and propose a novel grasping stabilizer focusing on stable tool-use. We apply this study to the five-fingered musculoskeletal hand installed in Fig.…”

Section: Contact State Changesmentioning

confidence: 99%

Stable Tool-Use with Flexible Musculoskeletal Hands by Learning the Predictive Model of Sensor State Transition

Kawaharazuka

Tsuzuki

Onitsuka

et al. 2020

2020 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

The flexible under-actuated musculoskeletal hand is superior in its adaptability and impact resistance. On the other hand, since the relationship between sensors and actuators cannot be uniquely determined, almost all its controls are based on feedforward controls. When grasping and using a tool, the contact state of the hand gradually changes due to the inertia of the tool or impact of action, and the initial contact state is hardly kept. In this study, we propose a system that trains the predictive network of sensor state transition using the actual robot sensor information, and keeps the initial contact state by a feedback control using the network. We conduct experiments of hammer hitting, vacuuming, and brooming, and verify the effectiveness of this study.

show abstract

Iterative Backpropagation Disturbance Observer with Forward Dynamics Model

Murooka

Hamaya

Drigalski

et al. 2021

2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)

View full text Add to dashboard Cite

Task-specific Self-body Controller Acquisition by Musculoskeletal Humanoids: Application to Pedal Control in Autonomous Driving

Cited by 9 publications

References 19 publications

Toward Autonomous Driving by Musculoskeletal Humanoids: A Study of Developed Hardware and Learning-Based Software

Toward Autonomous Driving by Musculoskeletal Humanoids: A Study of Developed Hardware and Learning-Based Software

Stable Tool-Use with Flexible Musculoskeletal Hands by Learning the Predictive Model of Sensor State Transition

Iterative Backpropagation Disturbance Observer with Forward Dynamics Model

Contact Info

Product

Resources

About