What question did this study set out to answer?

This research aims to enhance quadruped robots' abilities in object manipulation using legs as non-prehensile tools.

July 12, 2026MachinesOpen Access

A Hybrid RRT–PPO Framework for Leg-Based Object Manipulation of Quadruped Robots

View Full Paper

Ask AI

Bookmark

This research aims to enhance quadruped robots' abilities in object manipulation using legs as non-prehensile tools.
Developed a hybrid framework combining Rapidly exploring Random Trees (RRT) and Proximal Policy Optimization (PPO).
Evaluated in CoppeliaSim with a Spot-like quadruped pushing a box to a target position.
Trained agent on leg-pushing control using Bézier parameters and a leg-selection index.
Angular error ranged from 0.59° to 6.32° for box weights varying from 0.1 kg to 0.9 kg.
Position errors increased from 0.18 m to 0.64 m with the same variable.
Consistent rotation at ω≈4–5×10−4 rad/s with a fixed asymmetric Bézier action.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Randomized trial integrates global planning and adaptive control for effective object manipulation in quadruped robots, suggesting improved capabilities.

Cite This Study

Attias et al. (2026) studied this question.

synapsesocial.com/papers/6a53315f4f7abc118aded9be https://doi.org/10.3390/machines14070773

View Full Paper

Ask AI

Bookmark

Implication

Randomized trial integrates global planning and adaptive control for effective object manipulation in quadruped robots, suggesting improved capabilities.

A Hybrid RRT–PPO Framework for Leg-Based Object Manipulation of Quadruped Robots

Key Points

Discussion

Implication

Cite This Study

A Hybrid RRT–PPO Framework for Leg-Based Object Manipulation of Quadruped Robots

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider