Adaptive Mobile Robotics

Azad, A K M; Cowan, Noah J.; Tokhi, M. O.; Virk, GS; Eastman, Jason D.

doi:10.1142/8546

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, they have many degrees of freedom, which adds to the complexity of the task. While controllers for legged robots are often hand crafted [1], the design process is time consuming and would need to be repeated for a different body morphology. Thus a promising alternative to hand-crafting controllers is to train them through machine learning.…”

Section: Introductionmentioning

confidence: 99%

Single-unit pattern generators for quadruped locomotion

Morse

Risi

Snyder

et al. 2013

Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

Legged robots can potentially venture beyond the limits of wheeled vehicles. While creating controllers for such robots by hand is possible, evolutionary algorithms are an alternative that can reduce the burden of hand-crafting robotic controllers. Although major evolutionary approaches to legged locomotion can generate oscillations through popular techniques such as continuous time recurrent neural networks (CTRNNs) or sinusoidal input, they typically face a challenge in maintaining long-term stability. The aim of this paper is to address this challenge by introducing an effective alternative based on a new type of neuron called a singleunit pattern generator (SUPG). The SUPG, which is indirectly encoded by a compositional pattern producing network (CPPN) evolved by HyperNEAT, produces a flexible temporal activation pattern that can be reset and repeated at any time through an explicit trigger input, thereby allowing it to dynamically recalibrate over time to maintain stability. The SUPG approach, which is compared to CTRNNs and sinusoidal input, is shown to produce natural-looking gaits that exhibit superior stability over time, thereby providing a new alternative for evolving oscillatory locomotion.

show abstract

Section: Introductionmentioning

confidence: 99%

Single-unit pattern generators for quadruped locomotion

Morse

Risi

Snyder

et al. 2013

Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

A two-wheeled self-balancing robot with dynamics model

Ali

Hossen

2017

2017 4th International Conference on Advances in Electrical Engineering (ICAEE)

View full text Add to dashboard Cite

Dynamic legged locomotion for palm-size robots

2015

View full text Add to dashboard Cite

Minimally-actuated palm-size robots are capable of running at speeds greater than 2 meters per second (20 body lengths per second), with leg stride rates of greater than 20 Hz. In this dynamic regime, passive stabilization is needed for roll-and-pitch instability. However, we have found that certain roll-oscillation modes can be used for continuous high speed turning. Other continuous turning modes have also been identified, such as modulating foot contact location through foot compliance, and controlling differential leg velocity. For the small minimallyactuated robots examined, the dynamically enhanced roll-steer mode showed the best turning rate, of over 8 degrees per step, but only appears at certain running frequencies. Interstride phase and velocity control appears promising as a mode for in-plane maneuverability for under-actuated robots.

show abstract

Adaptive Mobile Robotics

Cited by 4 publications

References 0 publications

Single-unit pattern generators for quadruped locomotion

Single-unit pattern generators for quadruped locomotion

A two-wheeled self-balancing robot with dynamics model

Dynamic legged locomotion for palm-size robots

Contact Info

Product

Resources

About