Synthesis of dynamic locomotor behaviours using deep learning applied to realistic musculoskeletal models of bipedal and quadrupedal animals

Dr Monica A Daley (primary)
Comparative Biomedical Sciences
Royal Veterinary College
Professor John Hutchinson (secondary)
Comparative Biomedical Sciences
Royal Veterinary College

Abstract

Agile locomotor behavior requires effective integration of neural control with the physical dynamics of the musculoskeletal system. While advances in neuroscience continue to accelerate our understanding of the sensorimotor processes governing animal behavior, it remains less clear how musculoskeletal mechanics shape learning and behavior. The aim of this PhD project is to investigate the relationship between locomotor morphology and behaviour using anatomically realistic musculoskeletal models of exemplar bipedal and quadrupedal animals. The project will combine full-body musculoskeletal models with deep-reinforcement learning tools to simulate dynamic locomotor behaviors.


References

1) Birn-Jeffery, A.V., Hubicki, C.M., Blum, Y., Renjewski, D., Hurst, J.W. and Daley, M.A., 2014. Don’t break a leg: running birds from quail to ostrich prioritise leg safety and economy on uneven terrain. Journal of Experimental Biology, 217(21), pp.3786-3796.

2) Hubicki, C., Jones, M., Daley, M. and Hurst, J., 2015, May. Do limit cycles matter in the long run? stable orbits and sliding-mass dynamics emerge in task-optimal locomotion. In Robotics and Automation (ICRA), 2015 IEEE International Conference on (pp. 5113-5120). IEEE.

3) Hutchinson, J.R., Rankin, J.W., Rubenson, J., Rosenbluth, K.H., Siston, R.A. and Delp, S.L., 2015. Musculoskeletal modelling of an ostrich (Struthio camelus) pelvic limb: influence of limb orientation on muscular capacity during locomotion. PeerJ, 3, p.e1001.

4) Heess, N., Sriram, S., Lemmon, J., Merel, J., Wayne, G., Tassa, Y., Erez, T., Wang, Z., Eslami, A., Riedmiller, M. and Silver, D., 2017. Emergence of locomotion behaviours in rich environments. arXiv preprint arXiv:1707.02286.

5) Merel, J., Tassa, Y., Srinivasan, S., Lemmon, J., Wang, Z., Wayne, G. and Heess, N., 2017. Learning human behaviors from motion capture by adversarial imitation. arXiv preprint arXiv:1707.02201.

6) Daley, M.A., Channon, A.J., Nolan, G.S. and Hall, J., 2016. Preferred gait and walk–run transition speeds in ostriches measured using GPS-IMU sensors. Journal of Experimental Biology, 219(20), pp.3301-3308.


BBSRC Area
Animal disease, health and welfare
Area of Biology
BiotechnologyNeurobiologyPhysiology
Techniques & Approaches
Image ProcessingMathematics / StatisticsSimulation / Modelling