Deep reinforcement learning for robotics: A survey of real-world successes
Reinforcement learning (RL), particularly its combination with deep neural networks,
referred to as deep RL (DRL), has shown tremendous promise across a wide range of …
referred to as deep RL (DRL), has shown tremendous promise across a wide range of …
Lifelike agility and play in quadrupedal robots using reinforcement learning and generative pre-trained models
Abstract Knowledge from animals and humans inspires robotic innovations. Numerous
efforts have been made to achieve agile locomotion in quadrupedal robots through classical …
efforts have been made to achieve agile locomotion in quadrupedal robots through classical …
Learning speed adaptation for flight in clutter
Animals learn to adapt speed of their movements to their capabilities and the environment
they observe. Mobile robots should also demonstrate this ability to trade-off aggressiveness …
they observe. Mobile robots should also demonstrate this ability to trade-off aggressiveness …
Agile but safe: Learning collision-free high-speed legged locomotion
Legged robots navigating cluttered environments must be jointly agile for efficient task
execution and safe to avoid collisions with obstacles or humans. Existing studies either …
execution and safe to avoid collisions with obstacles or humans. Existing studies either …
Generalized animal imitator: Agile locomotion with versatile motion prior
The agility of animals, particularly in complex activities such as running, turning, jumping,
and backflipping, stands as an exemplar for robotic system design. Transferring this suite of …
and backflipping, stands as an exemplar for robotic system design. Transferring this suite of …
Two-stage learning of highly dynamic motions with rigid and articulated soft quadrupeds
Controlled execution of dynamic motions in quadrupedal robots, especially those with
articulated soft bodies, presents a unique set of challenges that traditional methods struggle …
articulated soft bodies, presents a unique set of challenges that traditional methods struggle …
Deep model predictive optimization
A major challenge in robotics is to design robust policies which enable complex and agile
behaviors in the real world. On one end of the spectrum, we have model-free reinforcement …
behaviors in the real world. On one end of the spectrum, we have model-free reinforcement …
Quadruped-Frog: Rapid Online Optimization of Continuous Quadruped Jumping
G Bellegarda, M Shafiee, ME Özberk… - arXiv preprint arXiv …, 2024 - arxiv.org
Legged robots are becoming increasingly agile in exhibiting dynamic behaviors such as
running and jumping. Usually, such behaviors are either optimized and engineered offline …
running and jumping. Usually, such behaviors are either optimized and engineered offline …
Cafe-mpc: A cascaded-fidelity model predictive control framework with tuning-free whole-body control
H Li, PM Wensing - arXiv preprint arXiv:2403.03995, 2024 - arxiv.org
This work introduces an optimization-based locomotion control framework for on-the-fly
synthesis of complex dynamic maneuvers. At the core of the proposed framework is a …
synthesis of complex dynamic maneuvers. At the core of the proposed framework is a …
Learning agile locomotion and adaptive behaviors via rl-augmented mpc
Y Chen, Q Nguyen - 2024 IEEE International Conference on …, 2024 - ieeexplore.ieee.org
In the context of legged robots, adaptive behavior involves adaptive balancing and adaptive
swing foot reflection. While adaptive balancing counteracts perturbations to the robot …
swing foot reflection. While adaptive balancing counteracts perturbations to the robot …