Whole-Body Active Compliance Control for Humanoid Robots with Robot Skin

Dean-León, Emmanuel; Guadarrama-Olvera, Julio Rogelio; Bergner, Florian; Cheng, Gordon

doi:10.1109/icra.2019.8793258

Cited by 26 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data driven methods are also promising for end-to-end models without an explicit kinematic/dynamic calibration (115). The most recent and comprehensive whole-body tactile sensing research was able to self-organize and self-calibrate 1,260 multi-modal sensing units, and implement a hierarchical task manager comprised of the fusion of a balance controller, a self-collision avoidance system, and a skin compliance controller (116).…”

Section: Reactionmentioning

confidence: 99%

Electronic skins and machine learning for intelligent soft robots

et al. 2020

View full text Add to dashboard Cite

Soft robots have garnered interest for real-world applications because of their intrinsic safety embedded at the material level. These robots use deformable materials capable of shape and behavioral changes and allow conformable physical contact for manipulation. Yet, with the introduction of soft and stretchable materials to robotic systems comes a myriad of challenges for sensor integration, including multimodal sensing capable of stretching, embedment of high-resolution but large-area sensor arrays, and sensor fusion with an increasing volume of data. This Review explores the emerging confluence of e-skins and machine learning, with a focus on how roboticists can combine recent developments from the two fields to build autonomous, deployable soft robots, integrated with capabilities for informative touch and proprioception to stand up to the challenges of real-world environments.

show abstract

Section: Reactionmentioning

confidence: 99%

Electronic skins and machine learning for intelligent soft robots

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In this section, we describe how we integrate the multimodal tactile signals of our robot skin into control systems to enhance the reactiveness of robots in physical human-robot interaction scenarios. We use two different approaches: one is based on a robot-dependent sensory-motor map [63] and the second is a more general approach to handle different robots with distinct control interfaces [64], [65].…”

Section: R O B O T S K I N C O N T R O L F R a M E W O R Kmentioning

confidence: 99%

A Comprehensive Realization of Robot Skin: Sensors, Sensing, Control, and Applications

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is known that humans use their sense of touch to compensate for errors associated with their visual and hearing systems. Humanoids can also benefit from the contribution of their tactile sensing for higher accuracy during the overall balancing and interaction operations [11][12][13]. While enhancing humanoids balance and interaction mechanisms increases the possibility of close-proximity human-robot interaction, it also contributes to the aspect of physical HRI's safety.…”

Section: Introductionmentioning

confidence: 99%

“…Overall the employment of tactile sensing in a broad sense seems to enhance safe humanoid robot interaction [15]. Currently humanoid robots use tactile, and force sensors which among other things are used for effective pedal balancing purposes [11][12][13]. There are some humanoid robots that are equipped with tactile sensors in their hands and other body parts [13].…”

Section: Introductionmentioning

confidence: 99%

“…Currently humanoid robots use tactile, and force sensors which among other things are used for effective pedal balancing purposes [11][12][13]. There are some humanoid robots that are equipped with tactile sensors in their hands and other body parts [13]. The utilization of such sensors all over the humanoid's body is thought to enable the robot to have tactile sensing comparable to a human and thus, a higher possibility of performing safe manoeuvres.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-time Collision Detection for Position-Controlled Humanoid Robots

Ramírez-Serrano¹,

Moghaddasi²

2020

International Conference of Control, Dynamic Systems, and Robotics

View full text Add to dashboard Cite

Humanoid robots (humanoids), at least in theory, can assist humans and work with them in cluttered and confined environments. However, further developments are needed to fully enable them to work in close proximity (even in physical interactions) with humans while not risking the safety of themselves and the objects and people around them. Current methods have not been fully successful in preparing humanoids for 100% safe physical Human Robot Interaction (HRI) due partially to the unresolved challenges of detecting the characteristics of the surrounding environment. Furthermore, current humanoids employ expensive and fragile equipment making them costly, thus limiting humanity of using them. This paper presents a novel real-time and hardware inexpensive collision detection methodology that employs signals from the robots' motor joints and data processing capabilities from the computers running the robot. The approach enables the safe close-proximity HRI for position-controlled humanoids that minimizes any negative effects caused by the detected collision. Using the proposed algorithm, humanoids can speedily identify the joint(s) responsible for the collision and the affected joints from which effective path planning movement control can be determined. Experimental results using a life-size humanoid robot having 29 degrees of freedom are presented that demonstrates the applicability of the proposed approach.

show abstract

Whole-Body Active Compliance Control for Humanoid Robots with Robot Skin

Cited by 26 publications

References 23 publications

Electronic skins and machine learning for intelligent soft robots

Electronic skins and machine learning for intelligent soft robots

A Comprehensive Realization of Robot Skin: Sensors, Sensing, Control, and Applications

Real-time Collision Detection for Position-Controlled Humanoid Robots

Contact Info

Product

Resources

About