Design Optimization of Musculoskeletal Humanoids with Maximization of Redundancy to Compensate for Muscle Rupture

Kawaharazuka, Kento; Toshimitsu, Yasunori; Nishiura, Manabu; Koga, Yuya; Omura, Yusuke; Asano, Yuki; Okada, Kei; Kawasaki, Koji; Inaba, Masayuki

doi:10.1109/iros51168.2021.9636845

Cited by 6 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…with brute force search. [14] optimizes muscle Jacobian for a musculoskeletal robot by genetic algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…Here, the wire arrangement configuration is mainly divided into two types: a type with constant moment arm using pulleys [6], [8], [9], [13], [14], and a type in which the moment arm changes depending on the joint angle by expressing the wire route with its start, relay, and end points [7], [10]- [12]. Note that for the type with constant moment arm, the moment arm can be designed directly by the pulley radius, and it is easy to guarantee the moment arm at various joint angles, but the ease of wire arrangement is lost because it is difficult to obtain large moment arm due to the large pulleys placed at all joints.…”

Section: Introductionmentioning

confidence: 99%

“…Note that for the type with constant moment arm, the moment arm can be designed directly by the pulley radius, and it is easy to guarantee the moment arm at various joint angles, but the ease of wire arrangement is lost because it is difficult to obtain large moment arm due to the large pulleys placed at all joints. In terms of optimization methods, there are two types: those that deal mainly with continuous values and can be optimized analytically [6], [9], [11], [12], and those that use black-box optimization for discrete values or other complex settings [7], [8], [10], [13], [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Continuous Jumping of a Parallel Wire-Driven Monopedal Robot RAMIEL Using Reinforcement Learning

Kawaharazuka

Suzuki

Okada

et al. 2022

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

We have developed a parallel wire-driven monopedal robot, RAMIEL, which has both speed and power due to the parallel wire mechanism and a long acceleration distance. RAMIEL is capable of jumping high and continuously, and so has high performance in traveling. On the other hand, one of the drawbacks of a minimal parallel wire-driven robot without joint encoders is that the current joint velocities estimated from the wire lengths oscillate due to the elongation of the wires, making the values unreliable. Therefore, despite its high performance, the control of the robot is unstable, and in 10 out of 16 jumps, the robot could only jump up to two times continuously. In this study, we propose a method to realize a continuous jumping motion by reinforcement learning in simulation, and its application to the actual robot. Because the joint velocities oscillate with the elongation of the wires, they are not used directly, but instead are inferred from the time series of joint angles. At the same time, noise that imitates the vibration caused by the elongation of the wires is added for transfer to the actual robot. The results show that the system can be applied to the actual robot RAMIEL as well as to the stable continuous jumping motion in simulation.

show abstract

“…with brute force search. [14] optimizes muscle Jacobian for a musculoskeletal robot by genetic algorithm.…”

Section: Introductionmentioning

confidence: 99%