Development of Amphibious Humanoid for Behavior Acquisition on Land and Underwater

Makabe, Tasuku; Anzai, Tomoki; Kakiuchi, Yohei; Okada, Kei; Inaba, Masayuki

doi:10.1109/humanoids47582.2021.9555671

Cited by 6 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As detailed in Section III-A, we use a low-rigidity plasticmade humanoid robot, KXR [4], for our experiments. We define θ as θ s−p θ s−y θ e−p θ a−p T , representing the commanded joint angle, which include shoulder pitch and yaw angles (s-p, s-y), elbow pitch angle (e-p), and ankle pitch angle (a-p) of KXR.…”

Section: A Network Structurementioning

confidence: 99%

“…In this study, we utilized a low-rigidity humanoid robot, KXR [4], made of plastic, as shown in Fig. 1.…”

Section: A Experimental Setupmentioning

confidence: 99%

“…Various types of robots have been developed over the years. While there are robots with high rigidity and strong force capabilities, commonly found in industrial applications [1], [2], there exist low-rigidity robots constructed with rubber or plastic-made links and joints [3], [4]. The development of these robots can be driven by different factors, such as the pursuit of flexibility in soft robotics [5], cost considerations, or the need for lightweight design.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Robotic Tool-Tip Control Learning Considering Online Changes in Grasping State

Kawaharazuka

Okada

Inaba

2021

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

Various robots have been developed so far; however, we face challenges in modeling the low-rigidity bodies of some robots. In particular, the deflection of the body changes during tool-use due to object grasping, resulting in significant shifts in the tool-tip position and the body's center of gravity. Moreover, this deflection varies depending on the weight and length of the tool, making these models exceptionally complex. However, there is currently no control or learning method that takes all of these effects into account. In this study, we propose a method for constructing a neural network that describes the mutual relationship among joint angle, visual information, and tactile information from the feet. We aim to train this network using the actual robot data and utilize it for tool-tip control. Additionally, we employ Parametric Bias to capture changes in this mutual relationship caused by variations in the weight and length of tools, enabling us to understand the characteristics of the grasped tool from the current sensor information. We apply this approach to the whole-body tool-use on KXR, a low-rigidity plastic-made humanoid robot, to validate its effectiveness.

show abstract

Section: A Network Structurementioning

confidence: 99%

“…In this study, we utilized a low-rigidity humanoid robot, KXR [4], made of plastic, as shown in Fig. 1.…”

Section: A Experimental Setupmentioning

confidence: 99%