Supplement media for Proactive Body Joint Adaptation for Energy-Efficient Locomotion of Bio-Inspired Multi-Segmented Robots

Citation Author(s):
Jettanan
Homchanthanakul
Bio-inspired Robotics and Neural Engineering Lab, Vidyasirimedhi Institute of Science and Technology
Poramate
Manoonpong
Bio-inspired Robotics and Neural Engineering Lab, Vidyasirimedhi Institute of Science and Technology
Submitted by:
Jettanan Homcha...
Last updated:
Thu, 01/05/2023 - 02:49
DOI:
10.1109/LRA.2023.3234773
Data Format:
*.mp4
Research Article Link:
Proactive Body Joint Adaptation for Energy-Efficient Locomotion of Bio-Inspired Multi-Segmented Robots
Links:
Proactive Body Joint Adaptation
License:
Creative Commons Attribution
212 Views
Categories:
Artificial Intelligence
Signal Processing
Other
Keywords:
Body-joint adaptation, proactive control, correlation-based learning, bio-inspired robotics, multi-segment robot, multi-legged robot
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

Typically, control strategies for legged robots have been developed to adapt their leg movements to deal with complex terrain. When the legs are extended in search of ground contact to support the robot body, this can result in the center of gravity (CoG) being raised higher from the ground and can lead to unstable locomotion if it deviates from the support polygon. An alternative approach is body adaptation, inspired by millipede/centipede locomotion behavior, which can result in low ground clearance and stable locomotion. In this study, we propose novel proactive neural control with online unsupervised learning, allowing multi-segmented, legged robots to proactively adapt their body to follow the surface contour and maintain efficient ground contact. Our approach requires neither kinematics nor environmental models. It relies solely on proprioceptive sensory feedback and short-term memory, enabling the robots to deal with complex 3D terrains. In comparison to traditional reflex-based control, our approach results in smoother and more energy-efficient robot locomotion on terrains with concave and convex curves or slopes of varying degrees in both simulation and real-world implementation.

Instructions: 

Supplement media for Proactive Body Joint Adaptation for Energy-Efficient Locomotion of Bio-Inspired Multi-Segmented Robots

 

There are seven supplementary videos illustrating the inspiration, process, and performance of our framework in different situations and platforms including simulation and real-world implementation.

 

Supplementary video 1 illustrates "The millipede locomotion on curved terrain."

Supplementary video 2 illustrates "The experiment to observe the robot's behavior using body-joint control on terrain adaptation."

Supplementary video 3 illustrates "The experiment of proactive body-joint control on the predictive weight learning process."

Supplementary video 4 illustrates "The experiment of proactive body-joint control on the different terrains in simulation."

Supplementary video 5 illustrates "The experiment of comparison between proactive body-joint control and traditional leg adaptation on 30-deg up and down ramps."

Supplementary video 6 illustrates "The experiment of comparison between proactive body-joint control and reflex-based control in real-world implementation."

Supplementary video 7 illustrates "The experiment of proactive body-joint control in a real-world outdoor environment of four-segmented robot."

 

The multimedia file has the standard mp4 file. All the common video players, such as Window media player and VLC media player, can run the attached files.

Funding Agency: 
the PTT Exploration and Production Public Co. Ltd. under the FREELANDER project
Grant Number: 
3450024742

Dataset Files

LOGIN TO ACCESS DATASET FILES

 

QUESTIONS?