Exploring Internal Simulation of Perception in Mobile Robots
(2001) 86. p.107-113- Abstract
- Based on a neuroscientific hypothesis, this paper explores the possibility of an ‘inner world’ based on internal simulation of perception. We present three sets of experiments with a possible minimal model, using a simulated Khepera robot controlled by a simple recurrent connectionist network. Using an evolutionary algorithm the robots are trained on increasingly complex tasks. In the first experiment, serving as a baseline, robots are simply trained to map sensory input to motor output such that they move around in an environment without collisions. In the second experiment robots are additionally trained on predicting the next time step’s sensory input. In the third experiment, finally, the robot’s own prediction replaces the actual... (More)
- Based on a neuroscientific hypothesis, this paper explores the possibility of an ‘inner world’ based on internal simulation of perception. We present three sets of experiments with a possible minimal model, using a simulated Khepera robot controlled by a simple recurrent connectionist network. Using an evolutionary algorithm the robots are trained on increasingly complex tasks. In the first experiment, serving as a baseline, robots are simply trained to map sensory input to motor output such that they move around in an environment without collisions. In the second experiment robots are additionally trained on predicting the next time step’s sensory input. In the third experiment, finally, the robot’s own prediction replaces the actual sensory input in order to investigate its capability to act ‘blindly’, i.e. in the temporary absence of external stimuli. Although only the first two experiments give positive results, we conclude that the experimental framework presented here should turn out useful in the investigation of more complex artificial neural models. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/4407144
- author
- Jirenhed, Dan-Anders LU ; Hesslow, Germund LU and Ziemke, Tom
- organization
- publishing date
- 2001
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- cognitive, sensory anticipation, inner world, simulation of perception, representation, robotics
- host publication
- Lund University Cognitive Studies
- editor
- Arras, Kai Oliver ; Baerveldt, Albert-Jan ; Balkenius, Christian ; Burgard, Wolfram and Siegwart, Roland
- volume
- 86
- pages
- 7 pages
- publisher
- Lund University
- language
- English
- LU publication?
- yes
- id
- e37372e7-4e38-4968-b7d6-e15924c3ed16 (old id 4407144)
- date added to LUP
- 2016-04-04 10:57:59
- date last changed
- 2022-05-16 12:08:52
@inproceedings{e37372e7-4e38-4968-b7d6-e15924c3ed16, abstract = {{Based on a neuroscientific hypothesis, this paper explores the possibility of an ‘inner world’ based on internal simulation of perception. We present three sets of experiments with a possible minimal model, using a simulated Khepera robot controlled by a simple recurrent connectionist network. Using an evolutionary algorithm the robots are trained on increasingly complex tasks. In the first experiment, serving as a baseline, robots are simply trained to map sensory input to motor output such that they move around in an environment without collisions. In the second experiment robots are additionally trained on predicting the next time step’s sensory input. In the third experiment, finally, the robot’s own prediction replaces the actual sensory input in order to investigate its capability to act ‘blindly’, i.e. in the temporary absence of external stimuli. Although only the first two experiments give positive results, we conclude that the experimental framework presented here should turn out useful in the investigation of more complex artificial neural models.}}, author = {{Jirenhed, Dan-Anders and Hesslow, Germund and Ziemke, Tom}}, booktitle = {{Lund University Cognitive Studies}}, editor = {{Arras, Kai Oliver and Baerveldt, Albert-Jan and Balkenius, Christian and Burgard, Wolfram and Siegwart, Roland}}, keywords = {{cognitive; sensory anticipation; inner world; simulation of perception; representation; robotics}}, language = {{eng}}, pages = {{107--113}}, publisher = {{Lund University}}, title = {{Exploring Internal Simulation of Perception in Mobile Robots}}, url = {{https://lup.lub.lu.se/search/files/5662932/4407145.pdf}}, volume = {{86}}, year = {{2001}}, }