Abstract
Autonomy and adaptability are key features in the design and construction of a robotic system capable of carrying out tasks in an unstructured and not predefined environment. Such adaptability is generally observed in animals, biological systems that often serve as inspiration models to the design of robots. The autonomy and adaptability of these systems partially arises from their ability to learn.
This work proposes a mechanism to enable a quadruped robot to detect and avoid an obstacle in its path. The detection is based on a Forward Internal Model trained in real-time to create estimations about the robot’s perceptive information. In order to avoid tripping on an obstacle, the detections are used to create a map of responses that will change the locomotion according to previous experience.
Both learning tasks occur in real time and are combined together, defining a Sensorimotor Map that enables the robot to learn to avoid an obstacle.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fukuoka, Y., Kimura, H., Cohen, A.H.: Adaptive dynamic walking of a quadruped robot on irregular terrain based on biological concepts. The International Journal of Robotics Research 22(3-4), 187 (2003)
Ilg, W., Albiez, J., Jedele, H., Berns, K., Dillmann, R.: Adaptive periodic movement control for the four legged walking machine bisam. In: Proceedings of the 1999 IEEE International Conference on Robotics and Automation, vol. 3, pp. 2354–2359. IEEE (1999)
Heliot, R., Espiau, B.: Multisensor input for cpg-based sensory—motor coordination. IEEE Transactions on Robotics 24(1), 191–195 (2008)
Buchli, J., Ijspeert, A.J.: Self-organized adaptive legged locomotion in a compliant quadruped robot. Auton. Robots 25, 331–347 (2008)
Doshi, F., Brunskill, E., Shkolnik, A., Kollar, T., Rohanimanesh, K., Tedrake, R., Roy, N.: Collision detection in legged locomotion using supervised learning. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007, pp. 317–322 (October 2007)
Kalakrishnan, M., Buchli, J., Pastor, P., Mistry, M., Schaal, S.: Fast, robust quadruped locomotion over challenging terrain. In: 2010 IEEE International Conference on Robotics and Automation (ICRA), pp. 2665–2670. IEEE (2010)
Wolpert, D.M., Kawato, M.: Multiple paired forward and inverse models for motor control. Neural Networks 11(7-8), 1317–1329 (1998)
Schröder-Schetelig, J., Manoonpong, P., Wörgötter, F.: Using efference copy and a forward internal model for adaptive biped walking. Autonomous Robots, 1–10 (2010)
Lewis, M.A., Bekey, G.A.: Gait adaptation in a quadruped robot. Autonomous Robots 12(3), 301–312 (2002)
Lewis, M.A., Simó, L.S.: Certain principles of biomorphic robots. Auton. Robots 11(3), 221–226 (2001)
Lewis, M.A., Simó, L.S.: Elegant stepping: A model of visually triggered gait adaptation. Connection Science 11(3), 331–344 (1999)
Matos, V., Santos, C.P.: Omnidirectional locomotion in a quadruped robot: A cpg-based approach. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3392–3397. IEEE (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Silva, P., Matos, V., Santos, C.P. (2012). Adaptive Quadruped Locomotion: Learning to Detect and Avoid an Obstacle. In: Ziemke, T., Balkenius, C., Hallam, J. (eds) From Animals to Animats 12. SAB 2012. Lecture Notes in Computer Science(), vol 7426. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33093-3_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-33093-3_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33092-6
Online ISBN: 978-3-642-33093-3
eBook Packages: Computer ScienceComputer Science (R0)