TY - GEN
T1 - A GWO Tuned Probabilistic Roadmap Approach for Coarse Mapping of Humanoid Robot in Inclined Terrain
AU - Kashyap, Abhishek Kumar
AU - Parhi, D. R.K.
AU - Kumar, Saroj
AU - Pandey, Anish
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2022
Y1 - 2022
N2 - Navigation for a humanoid robot in inclined terrain is a challenging activity in robotics. The goal of current research is to explore possible paths and optimize the footstep and identify routes that are optimum in reference to path length covered by the robot. A hybrid approach of Probabilistic Roadmap (PRM) and Grey wolf optimization (GWO) is proposed for humanoid NAO in terrain with an inclined plane and static obstacles. The sensory data such as obstacle distance in the right direction (RD), left direction (LD), and front direction (FD) are fed to the PRM approach, which provides stable walking for a humanoid robot with an interim driving angle (IDA). For optimum navigation and footstep adjustment for the inclined plane, the GWO approach is utilized. The proposed hybrid approach offers optimal driving angles (ODA) to navigate an inclined plane and guarantees the shortest distance. Simulation in flat terrain using the proposed approach and standalone approaches has been performed in a 3D simulator. The obtained convergence curve, travel distance, and time spent show that the NAO meets the objective in all situations, but that GWO tuned PRM approach is preferable to this objective. Further, the proposed approach has been analyzed in inclined terrain. Based on these results, the designed approach guarantees robustness and effectiveness.
AB - Navigation for a humanoid robot in inclined terrain is a challenging activity in robotics. The goal of current research is to explore possible paths and optimize the footstep and identify routes that are optimum in reference to path length covered by the robot. A hybrid approach of Probabilistic Roadmap (PRM) and Grey wolf optimization (GWO) is proposed for humanoid NAO in terrain with an inclined plane and static obstacles. The sensory data such as obstacle distance in the right direction (RD), left direction (LD), and front direction (FD) are fed to the PRM approach, which provides stable walking for a humanoid robot with an interim driving angle (IDA). For optimum navigation and footstep adjustment for the inclined plane, the GWO approach is utilized. The proposed hybrid approach offers optimal driving angles (ODA) to navigate an inclined plane and guarantees the shortest distance. Simulation in flat terrain using the proposed approach and standalone approaches has been performed in a 3D simulator. The obtained convergence curve, travel distance, and time spent show that the NAO meets the objective in all situations, but that GWO tuned PRM approach is preferable to this objective. Further, the proposed approach has been analyzed in inclined terrain. Based on these results, the designed approach guarantees robustness and effectiveness.
UR - https://www.scopus.com/pages/publications/85130300161
UR - https://www.scopus.com/pages/publications/85130300161#tab=citedBy
U2 - 10.1007/978-981-19-0296-3_11
DO - 10.1007/978-981-19-0296-3_11
M3 - Conference contribution
AN - SCOPUS:85130300161
SN - 9789811902956
T3 - Lecture Notes in Mechanical Engineering
SP - 111
EP - 124
BT - Applications of Computational Methods in Manufacturing and Product Design - Select Proceedings of IPDIMS 2020
A2 - Deepak, B. B.
A2 - Parhi, D. R.
A2 - Biswal, B. B.
A2 - Jena, Pankaj C.
PB - Springer Science and Business Media Deutschland GmbH
T2 - 2nd Conference of Innovative Product Design and Intelligent Manufacturing System, IPDIMS 2020
Y2 - 12 February 2021 through 13 February 2021
ER -