DRAMA, a connectionist architecture for learning in autonomous robots This work proposes a connectionist architecture, DRAMA, for dynamic control and learning of autonomous robots. DRAMA stands for dynamical recurrent associative memory architecture. It is a time-delay recurrent neural network, using Hebbian update rules. It allows learning of spatio-temporal regularities and time series in discrete sequences of inputs, in the face of an important amount of noise. The first part of this paper gives the mathematical description of the architecture and analyses theoretically and through numerical simulations its performance. The second part of this paper reports on the implementation of DRAMA in simulated and physical robotic experiments. Training and rehearsal of the DRAMA architecture is computationally fast and inexpensive, which makes the model particularly suitable for controlling `computationally-challenged ' robots. In the experiments, we use a basic hardware system with very limited computational capability and show that our robot can carry out real time computation and on-line learning of relatively complex cognitive tasks. In these experiments, two autonomous robots wander randomly in a fixed environment, collecting information about its elements. By mutually associating information of their sensors and actuators, they learn about physical regularities underlying their experience of varying stimuli. The agents learn also from their mutual interactions. We use a teacher-learner scenario, based on mutual following of the two agents, to enable transmission of a vocabulary from one robot to the other. Keywords: Time-delay recurrent neural network; Hebbian learning; spatio-temporal associations; unsupervised dynamical learning; autonomous robots. 3
|
1092
|
Finding Structure in Time
– Elman
- 1990
|
|
996
|
Self-Orgunkation and Associative Memory
– Kohonen
|
|
211
|
Learning and relearning in Boltzmann machines
– Hinton, Sejnowski
- 1986
|
|
197
|
Attractor dynamics and parallelism in a connectionist sequential machine
– Jordan
- 1986
|
|
155
|
Evolution of homing navigation in a real mobile robot
– Floreano, Mondada
- 1996
|
|
132
|
Organisation of Behaviour
– Hebb
- 1949
|
|
118
|
Grounding Adaptive Language Games in Robotic Agents
– STEELS, Vogt
- 1997
|
|
110
|
Neural Net Architectures for Temporal Sequence Processing’ in Andreas Weigand and Neil Gershenfeld (eds), Time Series Prediction – Forecasting Financial Failure and Understanding the Past
– Mozer
- 1993
|
|
109
|
Gradient Calculations for Dynamic Recurrent Neural Networks: A Survey
– Pearlmutter
- 1995
|
|
103
|
Reinforcement learning in the multi-robot domain
– Matarić
- 1997
|
|
102
|
Getting to know each other—artificial social intelligence for autonomous robots
– Dautenhahn
- 1995
|
|
93
|
Explanation-Based Neural Network Learning: A Lifelong Learning Approach
– Thrun
- 1996
|
|
74
|
Non-holographic associative memory
– Wilshaw, Buneman, et al.
- 1969
|
|
70
|
An adaptive communication protocol for cooperating mobile robots
– Yanco, Stein
- 1993
|
|
56
|
Self-organization and associative memory (3rd ed
– Kohonen
- 1989
|
|
50
|
Sensory-motor coordination: the metaphor and beyond
– Pfeifer, Scheier
- 1997
|
|
45
|
Robust world-modeling and navigation in a real world
– Zimmer
- 1996
|
|
43
|
Using emergent modularity to develop control systems for mobile robots", Adaptive Behavior 5
– Nolfi
- 1997
|
|
41
|
Grounding communication in autonomous robots: An experimental study
– Billard, Dautenhahn
- 1998
|
|
40
|
Grounding communication in situated, social robots
– Billard, Dautenhahn
- 1997
|
|
39
|
From perception-action loops to imitation processes: A bottom-up approach of learning by imitation
– Gaussier, Moga, et al.
- 1998
|
|
37
|
A qualitative approach to robot exploration and map-learning
– Kuipers, Byun
- 1987
|
|
34
|
Constructing maps for mobile robot navigation based on ultrasonic range data
– Kurz
- 1996
|
|
31
|
Experiments on human-robot communication with robota, an interactive learning and communicating doll robot
– Billard, Dautenhahn, et al.
- 1998
|
|
29
|
Learning to communicate through imitation in autonomous robots
– Billard, Hayes
- 1997
|
|
27
|
An on-line method to evolve behavior and to control a miniature robot in real time with genetic programming, Adaptive Behavior 5
– Nordin, Banzhaf
- 1997
|
|
22
|
Human-robot-communication and machine learning
– Klingspor, Demiris, et al.
- 1997
|
|
21
|
Backpropagation: Theory, Architectures and Applications, eds
– Chauvin, Rumelhart
- 1995
|
|
18
|
Hosoda K.: “Cooperative behavior acquisition for mobile robots in dynamically changing real worlds via visionbased reinforcement learning and development
– Asada, Uchibe
- 1999
|
|
17
|
Continuous-Time Temporal Back-Propagation with Adaptive Time Delays
– Day, Davenport
- 1993
|
|
17
|
Dynamic Recurrent Neural Networks: Theory and Applications
– Giles, Kuhn, et al.
- 1994
|
|
16
|
An Adaptive Communication Protocol for Cooperating Mobile Robots
– Yanco, Stein
- 1993
|
|
15
|
Nehmzow, Route Learning in Mobile Robots through SelfOrganisation
– Owen, Ulrich
- 1996
|
|
15
|
Transmitting communication skills through imitation in autonomous robots
– Billard, Hayes
- 1998
|
|
13
|
Iterative Retrieval of Sparsely Coded Associative Memory Patterns. Neural Networks
– Schwenker, Sommer, et al.
- 1996
|
|
12
|
D.W.: Computing with Neural Circuits: a Model. Science
– Hopfield, Tank
- 1986
|
|
10
|
a connectionist model for robot learning : Experiments in grounding communication through imitation in autonomous robots
– Billard, Drama
- 1998
|
|
7
|
Allo kazam, do you follow me? or learning to speak through imitation for social robots
– Billard
- 1996
|
|
5
|
Design, analysis, and comparison of robot learners
– Wyatt, Hoar, et al.
- 1998
|
|
4
|
Performance characteristics of the associative net
– Buckingham, Willshaw
- 1992
|
|
4
|
Learning spatio-temporal topology using an adaptive time-delay neural network
– Lin, Ligomenides, et al.
- 1993
|
|
4
|
The Case for a Realistic Mobile Robot Simulator
– Torrance, C
- 1992
|
|
4
|
Elements of Brain Design for Autonomous Agents
– Zrehen
- 1995
|
|
3
|
Capacity and Information Efficiency of a Brain-like Associative Net
– Graham, Willshaw
- 1994
|
|
2
|
Multiassociative Memory
– Kolen
- 1991
|
|
1
|
Improving recall in a sparse autoassociative memory
– Graham
- 1995
|
|
1
|
Episodic associative memories
– Hattori
- 1996
|
|
1
|
Generalisation of backpropagation to recurrent neural networks', Phys
– Pineda
- 1987
|
|
1
|
A Combinatorial Neural Network Exhibiting Episodic and Semantic Memory Properties for Spatio-Temporal Patterns
– Rinkus
- 1995
|
|
1
|
Dynamical Interactions Between Visual Attention, Learning and Behavior: An Experiment with a Vision-Based Mobile Robot
– Tani, Yamamoto, et al.
- 1997
|
