Biologically Inspired Neural Network for Trajectory Formation and Obstacle Avoidance

Glasius, R.; Komoda, A.; Gielen, Stan

doi:10.1007/978-1-4471-2063-6_177

Cited by 5 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the target neuron and with valleys at the locations of the ob stacle neurons. As we have proved (Glasius et al 1995), this activation landscape is unique and the condition lor equilib rium [dui (t) /dt] = 0 guarantees that no plateaus can exist.…”

Section: The Sensory Mapmentioning

confidence: 84%

“…Therefore, for each given initial position, target position and the set of obstacles, the sensory map contains the optimal solution (Glasius et al 1995) constructed by successive gra dient ascents to the top. This neural activity field is passed to the motor map neurons, and, in addition, neurons in the motor map receive an external input which codes the current state of the system.…”

Section: The Sensory Mapmentioning

confidence: 99%

“…Al though this procedure is shown to give the optimal path, it is not an unsupervised method, since it requires an external observer to compare the activities of neighboring neurons in order to decide which neuron should be the next in the path towards the target. Recently, variations of this distancetransform or wave-propagation method have been proposed (Prassler 1989;Glasius et al 1995) using topographically ordered maps.…”

Section: Introductionmentioning

confidence: 99%

“…However, vised methods have been reported for topographically or-dered maps and hierarchically organized topographically or dered neural networks are frequently found in the nervous system. With the local learning rule, these properties give the models by Glasius et al (1994Glasius et al ( , 1995 and Prassler (1989) a biologically plausible basis. In this paper we present a neu ral network which is an amalgamation of our two previous models.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A biologically inspired neural net for trajectory formation and obstacle avoidance

Glasius¹,

Komoda²,

Gielen³

1996

Biol. Cybern.

View full text Add to dashboard Cite

In this paper we present a biologically inspired two-layered neural network for trajectory formation and obstacle avoidance. The two topographically ordered neural maps consist of analog neurons having continuous dynamics. The first layer, the sensory map, receives sensory information and builds up an activity pattern which contains the optimal solution (i.e. shortest path without collisions) for any given set of current position, target positions and obstacle positions. Targets and obstacles are allowed to move, in which case the activity pattern in the sensory map will change accordingly. The time evolution of the neural activity in the second layer, the motor map, results in a moving cluster of activity, which can be interpreted as a population vector. Through the feedforward connections between the two layers, input of the sensory map directs the movement of the cluster along the optimal path from the current position of the cluster to the target position. The smooth trajectory is the result of the intrinsic dynamics of the network only. No supervisor is required. The output of the motor map can be used for direct control of an autonomous system in a cluttered environment or for control of the actuators of a biological limb or robot manipulator. The system is able to reach a target even in the presence of an external perturbation. Computer simulations of a point robot and a multi-joint manipulator illustrate the theory.

show abstract

Section: The Sensory Mapmentioning

confidence: 84%

Section: The Sensory Mapmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A biologically inspired neural net for trajectory formation and obstacle avoidance

Glasius¹,

Komoda²,

Gielen³

1996

Biol. Cybern.

View full text Add to dashboard Cite

show abstract

“…It was proved that the generated trajectory does not suffer from undesired local minimum. They later proposed another model (Glasius et al 1996) by cascading two neural network layers, where each layer has a similar structure. The second layer of this model was used to find the next robot configuration.…”

Section: Introductionmentioning

confidence: 99%

Neural network approach to collision free path-planning for robotic manipulators

Pashkevich¹,

Kazheunikau²,

Ruano³

2006

International Journal of Systems Science

View full text Add to dashboard Cite

The paper deals with collision free path-planning for industrial robotic manipulators A new efficient approach is proposed that is based on the topologically ordered neural network model. This model describes harmonic potential field of the robot configuration space, sampled by the non-regular grid. The developed path-planning algorithm takes into account highly-irregular shape of the obstacles of welding and assembling robotic cells, and provides reduced number of collision checking. The stability of the topologically ordered neural network is investigated. The algorithm has been successfully applied to the off-line programming of a robotic manufacturing cell for the automotive industry.

show abstract

Neural network approach to trajectory synthesis for robotic manipulators

Pashkevich

Kazheunikau

2005

J Intell Manuf

View full text Add to dashboard Cite

Biologically Inspired Neural Network for Trajectory Formation and Obstacle Avoidance

Cited by 5 publications

References 4 publications

A biologically inspired neural net for trajectory formation and obstacle avoidance

A biologically inspired neural net for trajectory formation and obstacle avoidance

Neural network approach to collision free path-planning for robotic manipulators

Neural network approach to trajectory synthesis for robotic manipulators

Contact Info

Product

Resources

About