A Data Mining Approach to Predict Falls in Humanoid Robot Locomotion
The inclusion of perceptual information in the operation of a dynamic robot (interacting with its environment) can provide valuable insight about its environment and increase robustness of its behaviour. In this regard, the concept of Associative Skill Memories (ASMs) has provided a great contributions regarding an effective and practical use of sensor data, under a simple and intuitive framework [2, 13]. Inspired by , this paper presents a data mining solution to the fall prediction problem in humanoid biped robotic locomotion. Sensor data from a large number of simulations was recorded and four data mining algorithms were applied with the aim of creating a classifier that properly identifies failure conditions. Using Support Vector Machines, on top of sensor data from a large number of simulation trials, it was possible to build an accurate and reliable offline fall predictor, achieving accuracy, sensitivity and specificity values up to 95.6%, 96.3% and 94.5%, respectively.
Unable to display preview. Download preview PDF.
- 1.André, J., Santos, C., Costa, L.: Path integral learning of multidimensional movement trajectories. In: Proceedings of the International Conference of Numerical Analysis and Applied Mathematics 2013 (ICNAAM 2013), Rhodes, Greece (2013)Google Scholar
- 5.Christensen, A.L.: Fault Detection in Autonomous Robots. Phd, Université Libre de Bruxelles (2008)Google Scholar
- 7.Holte, R.C.: Very simple classification rules perform well on most commonly used datasets. doi:10.1.1.103.7226Google Scholar
- 8.Matos, V., Santos, C.P.: Central pattern generators with phase regulation for the control of humanoid locomotion. In: IEEE-RAS International Conference on Humanoid Robots, Osaka, Japan (2012)Google Scholar
- 9.Owaki, D., Morikawa, L., Ishiguro, A.: Listen to body’s message: quadruped robot that fully exploits physical interaction between legs. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1950–1955. IEEE, Vilamoura (2012)Google Scholar
- 10.Tan, P.N., Steinbach, M., Kumar, V.: Introduction to data mining. In: Pearson Education, Inc. (2006)Google Scholar
- 11.Pastor, P., Kalakrishnan, M., Chitta, S., Theodorou, E., Schaal, S.: Skill learning and task outcome prediction for manipulation. In: 2011 IEEE International Conference on Robotics and Automation, pp. 3828–3834 (2011)Google Scholar
- 13.Pastor, P., Kalakrishnan, M., Righetti, L., Schaal, S.: Towards associative skill memories. In: 12th IEEE-RAS International Conference on Humanoid Robotics (Humanoids), Osaka, Japan, pp. 309–315 (2012)Google Scholar
- 14.Plagemann, C., Stachniss, C., Burgard, W.: Efficient failure detection for mobile robots using mixed-abstraction particle filters. In: European Robotics Symposium 2006, pp. 93–107 (2006)Google Scholar
- 15.Rapidminer: Predictive analytics reimagined. http://support.robotis.com/en/product/darwin-op.htm (accessed July 2015)