Neurobiologically inspired mobile robot navigation and planning

Cuperlier, Nicolas; Quoy, Mathias; Gaussier, Philippe

doi:10.3389/neuro.12.003.2007

Cited by 64 publications

(76 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Arleo and Gerstner (2000) and Chavarriaga et al (2005) use an -greedy scheme, in which novel actions are tested with small probability on each time step, while Foster et al (2000) use a soft-max selection where actions with high Q-values have a higher probability of being chosen. In robotic experiments (Cuperlier et al 2007;Barrera and Weitzenfeld 2007), the exploration is chosen when the animat cannot associate its location with any existing node in its topological map. In Girard et al (2005), the exploration is a random direction chosen among the other strategies, but the selection is not learned.…”

Section: The Role Of Random Explorationmentioning

confidence: 99%

Path planning versus cue responding: a bio-inspired model of switching between navigation strategies

et al. 2010

View full text Add to dashboard Cite

In this article, we describe a new computational model of switching between path-planning and cue-guided navigation strategies. It is based on three main assumptions: (i) the strategies are mediated by separate memory systems that learn independently and in parallel; (ii) the learning algorithms are different in the two memory systems-the cueguided strategy uses a temporal-difference (TD) learning rule to approach a visible goal, whereas the path-planning strategy relies on a place-cell-based graph-search algorithm to learn the location of a hidden goal; (iii) a strategy selection mechanism uses TD-learning rule to choose the most successful strategy based on past experience. We propose a novel criterion for strategy selection based on the directions of goal-oriented movements suggested by the different strategies. We show that the selection criterion based on this "common currency" is capable of choosing the best among TD-learning and planning strategies and can be used to solve navigational tasks in continuous state and action spaces. The model has been successfully applied to reproduce rat behavior in two water-maze tasks in which the two strategies were Laurent Dollé, Denis Sheynikhovich-First authorship shared.

show abstract

Section: The Role Of Random Explorationmentioning

confidence: 99%

Path planning versus cue responding: a bio-inspired model of switching between navigation strategies

et al. 2010

View full text Add to dashboard Cite

show abstract

“…The prefrontal cortex would use information about these transitions to create a cognitive map and use it to plan actions toward the fulfillment of specific goals. This model was later used on a real robot navigating in an indoor environment [12]. The aim of this paper is to reuse the principles of the model, result of a long series of experiments with mobile robots, and adapt them for planning in the proprioceptive space of a robotic arm.…”

Section: Adaptation Of a Bio-inspired Cognitive Map Model To Arm mentioning

confidence: 99%

“…In the original navigation architecture [12], the robot could find resources in its environment. To each type of resource corresponds a drive that represents the motivation of the robot to look for that kind of reward.…”

Section: Adaptation Of a Bio-inspired Cognitive Map Model To Arm mentioning

confidence: 99%

On-line learning and planning in a pick-and-place task demonstrated through body manipulation

Rengervé¹,

Hirel²,

Andry³

et al. 2011

2011 IEEE International Conference on Development and Learning (ICDL)

View full text Add to dashboard Cite

Abstract-When a robot is brought into a new environment, it has a very limited knowledge of what surrounds it and what it can do. One way to build up that knowledge is through exploration but it is a slow process. Programming by demonstration is an efficient way to learn new things from interaction. A robot can imitate gestures it was shown through passive manipulation. Depending on the representation of the task, the robot may also be able to plan its actions and even adapt its representation when further interactions change its knowledge about the task to be done. In this paper we present a bio-inspired neural network used in a robot to learn arm gestures demonstrated through passive manipulation. It also allows the robot to plan arm movements according to activated goals. The model is applied to learning a pick-and-place task. The robot learns how to pick up objects at a specific location and drop them in two different boxes depending on their color. As our system is continuously learning, the behavior of the robot can always be adapted by the human interacting with it. This ability is demonstrated by teaching the robot to switch the goals for both types of objects.

show abstract

“…The activity recorded in the CA pyramidal cells would not primarily originate from "place cells" but from "transition cells" coding for the transient states from one place to the next [2,3]. The reason for this proposal arose from two experimental findings.…”

Section: Introductionmentioning

confidence: 99%

“…In computational terms, in addition to the N place cells coding for states, the transition architecture requires the use of between 4N and 6N neurons in average to learn the transitions [3]. However the transition architecture shows its strength in complex tasks with multiple goals and motivations.…”

Section: Improvements Over Actor-critic Modelsmentioning

confidence: 99%

Why and How Hippocampal Transition Cells Can Be Used in Reinforcement Learning

Hirel

Gaussier

Quoy

et al. 2010

From Animals to Animats 11

View full text Add to dashboard Cite

Final draft version, accepted for publication as:Hirel, J., Gaussier, P., Quoy, M., Banquet, J.P.: Why and how hippocampal transition cells can be used in reinforcement learning. In Doncieux, S., Girard, B., Guillot, A. The original publication is available at www.springerlink.comAbstract. In this paper we present a model of reinforcement learning (RL) which can be used to solve goal-oriented navigation tasks. Our model supposes that transitions between places are learned in the hippocampus (CA pyramidal cells) and associated with information coming from path-integration. The RL neural network acts as a bias on these transitions to perform action selection. RL originates in the basal ganglia and matches observations of reward-based activity in dopaminergic neurons. Experiments were conducted in a simulated environment. We show that our model using transitions and inspired by Q-learning performs more efficiently than traditional actor-critic models of the basal ganglia based on temporal difference (TD) learning and using static states.

show abstract

Neurobiologically inspired mobile robot navigation and planning

Cited by 64 publications

References 98 publications

Path planning versus cue responding: a bio-inspired model of switching between navigation strategies

Path planning versus cue responding: a bio-inspired model of switching between navigation strategies

On-line learning and planning in a pick-and-place task demonstrated through body manipulation

Why and How Hippocampal Transition Cells Can Be Used in Reinforcement Learning

Contact Info

Product

Resources

About