{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["25(5)"],"submitter":["Azimi D"],"pubmed_abstract":["This study introduces a hierarchical reinforcement learning (RL) framework tailored to object manipulation tasks by quadrupedal robots, emphasizing their real-world deployment. The proposed approach adopts a sensor-driven control structure capable of addressing challenges in dense and cluttered environments filled with walls and obstacles. A novel reward function is central to the method, incorporating sensor-based obstacle observations to optimize the decision-making. This design minimizes the computational demands while maintaining adaptability and robust functionality. Simulated trials conducted in NVIDIA Isaac Sim, utilizing ANYbotics quadrupedal robots, demonstrated a high manipulation accuracy, with a mean positioning error of 11 cm across object-target distances of up to 10 m. Furthermore, the RL framework effectively integrates path planning in complex environments, achieving energy-efficient and stable operations. These findings establish the framework as a promising approach for advanced robotics requiring versatility, efficiency, and practical deployability."],"journal":["Sensors (Basel, Switzerland)"],"pagination":["1565"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11902496"],"repository":["biostudies-literature"],"pubmed_title":["Hierarchical Reinforcement Learning for Quadrupedal Robots: Efficient Object Manipulation in Constrained Environments."],"pmcid":["PMC11902496"],"pubmed_authors":["Hoseinnezhad R","Azimi D"],"additional_accession":[]},"is_claimable":false,"name":"Hierarchical Reinforcement Learning for Quadrupedal Robots: Efficient Object Manipulation in Constrained Environments.","description":"This study introduces a hierarchical reinforcement learning (RL) framework tailored to object manipulation tasks by quadrupedal robots, emphasizing their real-world deployment. The proposed approach adopts a sensor-driven control structure capable of addressing challenges in dense and cluttered environments filled with walls and obstacles. A novel reward function is central to the method, incorporating sensor-based obstacle observations to optimize the decision-making. This design minimizes the computational demands while maintaining adaptability and robust functionality. Simulated trials conducted in NVIDIA Isaac Sim, utilizing ANYbotics quadrupedal robots, demonstrated a high manipulation accuracy, with a mean positioning error of 11 cm across object-target distances of up to 10 m. Furthermore, the RL framework effectively integrates path planning in complex environments, achieving energy-efficient and stable operations. These findings establish the framework as a promising approach for advanced robotics requiring versatility, efficiency, and practical deployability.","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Mar","modification":"2025-04-04T13:12:13.16Z","creation":"2025-04-04T13:12:13.16Z"},"accession":"S-EPMC11902496","cross_references":{"pubmed":["40096360"],"doi":["10.3390/s25051565"]}}