EFGCL adds external assistive forces during RL training to let legged robots physically experience successful dynamic motions early, accelerating learning of jumps and flips by about 2x and enabling behaviors conventional methods cannot acquire.
High-speed control and navigation for quadrupedal robots on complex and discrete terrain
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.RO 4years
2026 4verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
LineRides enables commandable bicycle robot stunts via line-guided RL that uses spatial guidelines, a tracking margin for feasibility, distance-based progress, and sparse key-orientations.
DreamTIP adds LLM-identified task-invariant properties as auxiliary targets in Dreamer's world model plus a mixed-replay adaptation step, delivering 28.1% average simulated transfer gains and 100% real-world climb success versus 10% for baselines.
A hierarchical RL framework with an explicit mass estimation module enables dynamic concurrent locomotion and manipulation on a quadruped with arm, achieving 86% success in simulation up to 2.3 kg and 73% in real tests up to 1.3 kg across varied heights and object properties.
citing papers explorer
-
EFGCL: Learning Dynamic Motion through Spotting-Inspired External Force Guided Curriculum Learning
EFGCL adds external assistive forces during RL training to let legged robots physically experience successful dynamic motions early, accelerating learning of jumps and flips by about 2x and enabling behaviors conventional methods cannot acquire.
-
LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts
LineRides enables commandable bicycle robot stunts via line-guided RL that uses spatial guidelines, a tracking margin for feasibility, distance-based progress, and sparse key-orientations.
-
Learning Task-Invariant Properties via Dreamer: Enabling Efficient Policy Transfer for Quadruped Robots
DreamTIP adds LLM-identified task-invariant properties as auxiliary targets in Dreamer's world model plus a mixed-replay adaptation step, delivering 28.1% average simulated transfer gains and 100% real-world climb success versus 10% for baselines.
-
Learning Dynamic Pick-and-Place for a Legged Manipulator
A hierarchical RL framework with an explicit mass estimation module enables dynamic concurrent locomotion and manipulation on a quadruped with arm, achieving 86% success in simulation up to 2.3 kg and 73% in real tests up to 1.3 kg across varied heights and object properties.