Adaptive Navigation Strategies in Evolutionary Robotics Controllers with Location Perception

Author(s):  
Antin Phillips ◽  
Mathys C. Du Plessis
2020 ◽  
Vol 717 ◽  
pp. 137147
Author(s):  
Margret Sibylle Engel ◽  
Janina Fels ◽  
Carmella Pfaffenbach

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Abdallah Daddi-Moussa-Ider ◽  
Hartmut Löwen ◽  
Benno Liebchen

AbstractAs compared to the well explored problem of how to steer a macroscopic agent, like an airplane or a moon lander, to optimally reach a target, optimal navigation strategies for microswimmers experiencing hydrodynamic interactions with walls and obstacles are far-less understood. Here, we systematically explore this problem and show that the characteristic microswimmer-flow-field crucially influences the navigation strategy required to reach a target in the fastest way. The resulting optimal trajectories can have remarkable and non-intuitive shapes, which qualitatively differ from those of dry active particles or motile macroagents. Our results provide insights into the role of hydrodynamics and fluctuations on optimal navigation at the microscale, and suggest that microorganisms might have survival advantages when strategically controlling their distance to remote walls.


Robotics ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 1
Author(s):  
Victor Massagué Respall ◽  
Stefano Nolfi

We investigate whether standard evolutionary robotics methods can be extended to support the evolution of multiple behaviors by forcing the retention of variations that are adaptive with respect to all required behaviors. This is realized by selecting the individuals located in the first Pareto fronts of the multidimensional fitness space in the case of a standard evolutionary algorithms and by computing and using multiple gradients of the expected fitness in the case of a modern evolutionary strategies that move the population in the direction of the gradient of the fitness. The results collected on two extended versions of state-of-the-art benchmarking problems indicate that the latter method permits to evolve robots capable of producing the required multiple behaviors in the majority of the replications and produces significantly better results than all the other methods considered.


2004 ◽  
Vol 24 (4) ◽  
pp. 475-493 ◽  
Author(s):  
Jan M. Wiener ◽  
Alexander Schnee ◽  
Hanspeter A. Mallot

Robotica ◽  
2009 ◽  
Vol 28 (3) ◽  
pp. 465-475 ◽  
Author(s):  
Edith Heußlein ◽  
Blair W. Patullo ◽  
David L. Macmillan

SUMMARYBiomimetic applications play an important role in informing the field of robotics. One aspect is navigation – a skill automobile robots require to perform useful tasks. A sub-area of this is search strategies, e.g. for search and rescue, demining, exploring surfaces of other planets or as a default strategy when other navigation mechanisms fail. Despite that, only a few approaches have been made to transfer biological knowledge of search mechanisms on surfaces along the ground into biomimetic applications. To provide insight for robot navigation strategies, this study describes the paths a crayfish used to explore terrain. We tracked movement when different sets of sensory input were available. We then tested this algorithm with a computer model crayfish and concluded that the movement of C. destructor has a specialised walking strategy that could provide a suitable baseline algorithm for autonomous mobile robots during navigation.


Author(s):  
Nuria Jaumot-Pascual ◽  
Christina B. Silva ◽  
Audrey Martinez-Gudaoakkam ◽  
Maria Ong

Sign in / Sign up

Export Citation Format

Share Document