Abstract:
Vision-based perception gives autonomous robots the ability to perform a varied set of tasks, due to the great amount and quality of information it procures. Although Reinforcement Learning (RL) is a learning model that has made a great impact in the autonomous robots field, its application to vision-based perception has been limited. One of the main reasons for this fact is the size of the state space: raw images are usually simply too big to be used as states for the direct application of RL techniques. In this work, we present a method that uses the linear Hough Transform to detect straight lines in captured images. Using a state representation based on small number of straight lines inferred from images, we can reduce the size of state space, making it possible to use standard RL algorithms, such as Q-Learning. As a part of the method, we also present a. model-free exploration technique based on e-greedy action selection strategy. We carry out a series of experiments in order to verify the method for the task of navigating through a corridor with a vision-based mobile robot, either on a robot simulator and on a real vision-based minirobot called FenBot.
Registro:
Documento: |
Conferencia
|
Título: | Reinforcement learning for vision based mobile robots using the Hough Transform |
Autor: | Pedrc, S.; De Cristóforis, P.; Bendersky, D.; Santos, J. |
Ciudad: | Buenos Aires |
Filiación: | Departamento de Computación, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, Argentina
|
Palabras clave: | Hough transform; Large state space size; Reinforcement learning; Vision-based mobile robots; Feature extraction; Hough transforms; Mobile robots; Navigation; Exploration techniques; ITS applications; Large state space size; Learning for vision; Quality of information; State representation; Vision-based mobile robots; Vision-based perception; Reinforcement learning |
Año: | 2007
|
Volumen: | 216
|
Página de inicio: | 161
|
Página de fin: | 168
|
Título revista: | 4th International Symposium on Autonomous Minirobots for Research and Edutainment, AMiRE 2007
|
Título revista abreviado: | Auton. Minirobots Res. Edutainment, AMiRE - Proc. Int. AMiRE Symp.
|
Registro: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_NIS12835_v216_n_p161_Pedrc |
Referencias:
- Watkins, C.J.C.H., (1989) Learning from Delayed Rewards, , PhD thesis, King's College, Cambridge
- Fernández Rebollo, F., (2002) Aprendizaje Por Refuerzo en Espacios de Estados Continuos, , PhD Thesis, Escuela Politécnica Superior, Universidad Carlos III de Madrid, Leganés
- Asada, M., Nöda, S., Tawaratsumida, S., Hosoda, K., Vision-based reinforcement learning for purposive behavior acquisition (1995) Proceedings of the IEEE International Conference on Robotics and Automation, , Osaka, Japan
- Distante, C., Anglani, A., Taurisano, F., Target reaching by using visual information and q-learning controllers (2000) Autonomous Robots, 9 (1), pp. 41-50. , August
- Gaskett, C., Fletcher, L., Zelinsky, A., Reinforcement learning for a vision based mobile robot (2000) Proc. of the IEEE/RS J International Conference on Intelligent Robots and Systems, , Takamatsu, Japan
- Martínez-Marín, T., Duckett, T., Fast reinforcement learning for vision-guided mobile robots (2005) Proc. of the 2005 IEEE International Conference on Robotics and Automation, , Barcelona, Spain
- Duda, R.O., Hart, P.E., Use of the hough transformation to detect lines and curves in pictures (1972) Comm ACM, 15 (1)
- Sonka, M., Hlavac, V., Boyle, R., (1998) Image Processing, Analysis, and Machine Vision, , ITP, PWS. Publishing, 2nd edition
- Thrun, S.B., (1992) Efficient Exploration in Reinforcement Learning, , Technical Report, School of Computer Science, Carnegie-Mellon University
- McCallum, A., Andrew, R., Efficient exploration in reinforcement learning with hidden state (1997) AAAI Fall Symposium on "Model-directed Autonomous Systems"
- Mataric, M.J., Reward functions for accelerated learning (1994) Machine Learning: Proceedings of the Eleventh International Conference, , New Brunswick, New Jersey, 10-13 JulyA4 -
Citas:
---------- APA ----------
Pedrc, S., De Cristóforis, P., Bendersky, D. & Santos, J.
(2007)
. Reinforcement learning for vision based mobile robots using the Hough Transform. 4th International Symposium on Autonomous Minirobots for Research and Edutainment, AMiRE 2007, 216, 161-168.
Recuperado de https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_NIS12835_v216_n_p161_Pedrc [ ]
---------- CHICAGO ----------
Pedrc, S., De Cristóforis, P., Bendersky, D., Santos, J.
"Reinforcement learning for vision based mobile robots using the Hough Transform"
. 4th International Symposium on Autonomous Minirobots for Research and Edutainment, AMiRE 2007 216
(2007) : 161-168.
Recuperado de https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_NIS12835_v216_n_p161_Pedrc [ ]
---------- MLA ----------
Pedrc, S., De Cristóforis, P., Bendersky, D., Santos, J.
"Reinforcement learning for vision based mobile robots using the Hough Transform"
. 4th International Symposium on Autonomous Minirobots for Research and Edutainment, AMiRE 2007, vol. 216, 2007, pp. 161-168.
Recuperado de https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_NIS12835_v216_n_p161_Pedrc [ ]
---------- VANCOUVER ----------
Pedrc, S., De Cristóforis, P., Bendersky, D., Santos, J. Reinforcement learning for vision based mobile robots using the Hough Transform. Auton. Minirobots Res. Edutainment, AMiRE - Proc. Int. AMiRE Symp. 2007;216:161-168.
Available from: https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_NIS12835_v216_n_p161_Pedrc [ ]