A Hybrid Multi-objective Evolutionary Approach for Optimal Path Planning of a Hexapod Robot

Carbone, Giuseppe; Nuovo, Alessandro Di

doi:10.1007/978-3-319-39636-1_10

Cited by 7 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the main challenges linked to the research and application of legged robots is to program gaits. Depending on the robot morphology and the number of actuators, the underlying kinematic model could quickly increase in complexity [1]- [4]. On the other side, to switch to a hand-tuning design and implementation, is not computationally efficient and requires high human efforts.…”

Section: Introductionmentioning

confidence: 99%

Neuroevolutive Algorithms for Learning Gaits in Legged Robots

Reyes

Escobar

2019

IEEE Access

View full text Add to dashboard Cite

Gait generation for legged robots is a challenging task typically requiring either a handtuning design or a kinematic model of the robot morphology to compute the movements, generating a high computational and time efforts. Neuroevolution algorithms with the ability to learn network topologies, such as Neuroevolution of Augmenting Topologies (NEAT), Hypercube-based NEAT (HyperNEAT), and τ -HyperNEAT, have been used in the computational community to learn gaits in legged robots. An extended version of HyperNEAT called ES-HyperNEAT, where the substrate hosting the nodes of the neural network evolves in shape, seems to be a promising algorithm to evaluate gait learning tasks. Using two four-legged robot platforms with different degrees of freedom (Quadratot and ARGOv2), we compared the performance of a variety of neuroevolution algorithms based on HyperNEAT for learning gaits. The comparative analysis of the results reveals that the three evaluated algorithms, HyperNEAT, τ -HyperNEAT and ES-HyperNEAT, successfully generate gaits given a fitness function. In particular, for the Quadratot platform, ES-HyperNEAT learns faster and better than the other two methods, a result that is not observed in the ArgoV2. Additionally, ES-HyperNEAT produces more phase changes between joints movement, resulting in more natural robot movements. Finally, ES-HyperNEAT produces complex substrates from simple Compositional Pattern Producing Networks, CPPN-NEAT, allowing the simplification of the underlying neural network.

show abstract

Section: Introductionmentioning

confidence: 99%

Neuroevolutive Algorithms for Learning Gaits in Legged Robots

Reyes

Escobar

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…ompared with wheeled robot and tracked robot, legged robots have stronger ability to rough terrain and is more flexible in complex environment of disaster rescue and terrain exploration [2] . The hexapod robot has better stability and load capacity among the legged robot, which can achieve various applications in different scenarios, such as lunar exploration, nuclear power plant inspection, etc., with a wealth of gait modes [1,3] . Thus the hexapod is required to keep strong stability and high adaptability.…”

mentioning

confidence: 99%

Hybrid Gait Planning of A Hexapod Robot

Wang

2020

Mod. Electron. Technol.

View full text Add to dashboard Cite

The adapotation of gaits pattern is a basic and important for the hexapod robot to move stably and efficiently, which depends on the servos of the robot’s legs, and also the body structure of the robot.This paper compares the tripod gait and the crab-inspired gait for a specific hexapod to move forward and move backward; turn left and turn right and integrates the two gaits to apply them under different conditions. The hexapod has three servos on each legs, thus the freedom level of each leg is three-degree. From the comparative experiment, this two gait patterns are suitable for different turning demands.

show abstract