Collision-free motion planning of multiarm robots using evolutionary algorithms

Rana, A.S.; Zalzala, A.M.S.

doi:10.1243/0959651971539902

Cited by 13 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One solution to this problem may be to use machine learning algorithms to learn to control nonlinear systems (Fleming and Purshouse, 2002;Rana and Zalzala, 1997). Here, we show that machine learning algorithms can learn to control the brain.…”

Section: Introductionmentioning

confidence: 82%

Learning to Control the Brain through Adaptive Closed-Loop Patterned Stimulation

Tafazoli

MacDowell

Che

et al. 2020

Preprint

View full text Add to dashboard Cite

Stimulation of neural activity is an important scientific and clinical tool, causally testing hypotheses and treating neurodegenerative and neuropsychiatric diseases. However, current stimulation approaches cannot flexibly control the pattern of activity in populations of neurons. To address this, we developed an adaptive, closed-loop stimulation (ACLS) system that uses patterned, multi-site electrical stimulation to control the pattern of activity in a population of neurons. Importantly, ACLS is a learning system; it monitors the response to stimulation and iteratively updates the stimulation pattern to produce a specific neural response. In silico and in vivo experiments showed ACLS quickly learns to produce specific patterns of neural activity (~15 minutes) and was robust to noise and drift in neural responses. In visual cortex of awake mice, ACLS learned electrical stimulation patterns that produced responses similar to the natural response evoked by visual stimuli. Similar to how repetition of a visual stimulus causes an adaptation in the neural response, the response to electrical stimulation was adapted when it was preceded by the associated visual stimulus. Altogether, our results show ACLS can learn, in real-time, to generate specific patterns of neural activity, providing a framework for using closed-loop learning to control neural activity.

show abstract

Section: Introductionmentioning

confidence: 82%

Learning to Control the Brain through Adaptive Closed-Loop Patterned Stimulation

Tafazoli

MacDowell

Che

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The avoidance of IEEE R10-HTC2013 Sendai, Japan, August 26-29, 2013 collision will guarantee free motion. Therefore, a circle method [11,12] is introduced to check the collision. The first potential collision might be between the links of two manipulators working in overlapping workspace, due to the fact that one manipulator might impede the other.…”

Section: The Collision Avoidancementioning

confidence: 99%

Using Electromagnetism-like algorithm and genetic algorithm to optimize time of task scheduling for dual manipulators

Abed

Sahari

Koh

et al. 2013

2013 IEEE Region 10 Humanitarian Technology Conference

View full text Add to dashboard Cite

A method based on Electromagnetism-Like algorithm (EM) and Genetic Algorithm (GA) is proposed to determine the time-optimal task scheduling for dual robot manipulators. GA is utilized to calculate the near-optimal task scheduling for the two robots. On top of that, the EM is recommended as a suitable alternative to obtain multiple solutions at each task points for both manipulators with less error. During the course of the tour, the dual robots move from point to point with less cycle time, while ensuring that no collision occurs between the two manipulators or between the dual manipulators and the static obstacles in the workspace. The movement and the configurations of the manipulators at the task points were visualized using a simulator developed via Visual Basic.Net. The method is verified using two simulators acting as examples for two identical four-link planar robots working in the environment, with square-shaped obstacles cluttered at different locations.

show abstract

“…For example, Rana and Zalzala (1997) presented an evolutionary algorithm for the collision-free path planning of multi-arm robots. A global path planning technique has been used where the paths are represented by a string of via-points that the robots have to pass through, connected together by cubic spline polynomials.…”

Section: Ga Emo and Their Utilization For Trajectory Planningmentioning

confidence: 99%

Trajectory planning for multiple unmanned vehicles under reciprocal constraints

Avigad

Eisenstadt

Cohen

2011

Engineering Optimization

View full text Add to dashboard Cite

In this article, a special class of trajectory optimization problems is formalized and solved. It involves the optimization of different unmanned vehicle (UMV) trajectories that are coupled through reciprocal constraints. It is shown in the article that searching for a solution to the problem at hand may stipulate not just planning a longer than the shortest possible path for each UMV, but also choosing slower travel speeds in order to co-ordinate between the UMVs. Although it seems that solving the problem possesses merits, it has been only partially treated before. Here it is solved by utilizing an evolutionary approach which involves a new algorithmic feature that allows striving towards the desired optimality. The approach is demonstrated and studied through solving and simulating several trajectory planning problems. It is shown that a wide range of problems might be related to that class of problems.

show abstract

Collision-free motion planning of multiarm robots using evolutionary algorithms

Cited by 13 publications

References 9 publications

Learning to Control the Brain through Adaptive Closed-Loop Patterned Stimulation

Learning to Control the Brain through Adaptive Closed-Loop Patterned Stimulation

Using Electromagnetism-like algorithm and genetic algorithm to optimize time of task scheduling for dual manipulators

Trajectory planning for multiple unmanned vehicles under reciprocal constraints

Contact Info

Product

Resources

About