Decoupled control of posture and trajectory of the hybrid wheel-legged robot hylos

Grand, Christophe; Benamar, Faiz; Plumet, Frédéric; Bidaud, Ph.

doi:10.1109/robot.2004.1302528

Cited by 69 publications

(30 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The physical robot is made from a Bioloid Kit and has been built after the wheeled-legged robot Hylos [20] designed for autonomous planetary/volcanic exploration. The reducedscale robot reproduces Hylos' degrees of freedom and its global geometry.…”

Section: A Robot and Experimental Set-upmentioning

confidence: 99%

The Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics

Koos

Mouret

Doncieux

2013

IEEE Trans. Evol. Computat.

216

184

View full text Add to dashboard Cite

Abstract-The reality gap, that often makes controllers evolved in simulation inefficient once transferred onto the physical robot, remains a critical issue in Evolutionary Robotics (ER). We hypothesize that this gap highlights a conflict between the efficiency of the solutions in simulation and their transferability from simulation to reality: the most efficient solutions in simulation often exploit badly modeled phenomena to achieve high fitness values with unrealistic behaviors. This hypothesis leads to the Transferability approach, a multi-objective formulation of ER in which two main objectives are optimized via a Pareto-based Multi-Objective Evolutionary Algorithm: (1) the fitness and (2) the transferability, estimated by a simulation-to-reality (STR) disparity measure. To evaluate this second objective, a surrogate model of the exact STR disparity is built during the optimization. This Transferability approach has been compared to two realitybased optimization methods, a noise-based approach inspired from Jakobi's minimal simulation methodology and a local search approach. It has been validated on two robotic applications: 1) a navigation task with an e-puck robot; 2) a walking task with an 8-DOF quadrupedal robot. For both experimental set-ups, our approach successfully finds efficient and well-transferable controllers only with about ten experiments on the physical robot.

show abstract

Section: A Robot and Experimental Set-upmentioning

confidence: 99%

The Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics

Koos

Mouret

Doncieux

2013

IEEE Trans. Evol. Computat.

216

184

View full text Add to dashboard Cite

show abstract

“…Introduction Figure 1.12 in a bounding gait, though underactuated, is able to move in several different gaits with the use of its hybrid style setup and even perform jumping manoeuvres. Finally, the hybrid quadruped robot Hylos [32][33][34][35][36][37], developed at the Pierre and Marie Curie University, serves as an inspiration for the controller presented in this thesis. Hylos is a relatively lightweight and small robot with pivoting wheels shown to efficiently adapt to uneven terrain (see Figure 1.14).…”

Section: Quadrupedal Platformsmentioning

confidence: 99%

“…Section 3.4 consists of an overview of the control methodology. Section 3.5 describes the differential kinematics model, which provides the foundation for the controller, while section 3.6 describes the modifications made relative to the original methodology in [36]. Section 3.7 details the simulation results obtained for posture tasks assigned to MHT and finally, section 3.8…”

Section: Simmechanics and Mscadams Modelmentioning

confidence: 99%

Kinematic control and posture optimization of a redundantly actuated quadruped robot

Thomson

Sharf

Beckman

2012

2012 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…To exploit such a gait variety, the task we want to achieve here consists in finding transferable walking gaits as fast as possible on a quadrupedal 8-DOF robot (Figure 1). The physical device is made from Bioloid Kit and has been built as a reduced scale model of the wheeled-legged robot Hylos [8] (Figure 1), designed for autonomous planetary/volcanic exploration. Each leg includes 4 Dynamixel AX-12+ Robot Actuators.…”

Section: Robot and Experimental Setupsmentioning

confidence: 99%

Crossing the reality gap in evolutionary robotics by promoting transferable controllers

Koos

Mouret

Doncieux

2010

Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

The reality gap, that often makes controllers evolved in simulation inefficient once transferred onto the real system, remains a critical issue in Evolutionary Robotics (ER); it prevents ER application to real-world problems. We hypothesize that this gap mainly stems from a conflict between the efficiency of the solutions in simulation and their transferability from simulation to reality: best solutions in simulation often rely on bad simulated phenomena (e.g. the most dynamic ones). This hypothesis leads to a multi-objective formulation of ER in which two main objectives are optimized via a Pareto-based Multi-Objective Evolutionary Algorithm: (1) the fitness and (2) the transferability. To evaluate this second objective, a simulation-to-reality disparity value is approximated for each controller. The proposed method is applied to the evolution of walking controllers for a real 8-DOF quadrupedal robot. It successfully finds efficient and well-transferable controllers with only a few experiments in reality.

show abstract

Decoupled control of posture and trajectory of the hybrid wheel-legged robot hylos

Cited by 69 publications

References 13 publications

The Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics

The Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics

Kinematic control and posture optimization of a redundantly actuated quadruped robot

Crossing the reality gap in evolutionary robotics by promoting transferable controllers

Contact Info

Product

Resources

About