Deep reinforcement learning for robotics: A survey of real-world successes

C Tang, B Abbatematteo, J Hu… - Annual Review of …, 2024 - annualreviews.org
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 …

Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation

Z Fu, TZ Zhao, C Finn - arXiv preprint arXiv:2401.02117, 2024 - arxiv.org
Imitation learning from human demonstrations has shown impressive performance in
robotics. However, most results focus on table-top manipulation, lacking the mobility and …

Ok-robot: What really matters in integrating open-knowledge models for robotics

P Liu, Y Orru, J Vakil, C Paxton, NMM Shafiullah… - arXiv preprint arXiv …, 2024 - arxiv.org
Remarkable progress has been made in recent years in the fields of vision, language, and
robotics. We now have vision models capable of recognizing objects based on language …

Robot parkour learning

Z Zhuang, Z Fu, J Wang, C Atkeson… - arXiv preprint arXiv …, 2023 - arxiv.org
Parkour is a grand challenge for legged locomotion that requires robots to overcome various
obstacles rapidly in complex environments. Existing methods can generate either diverse …

Vlfm: Vision-language frontier maps for zero-shot semantic navigation

N Yokoyama, S Ha, D Batra, J Wang… - … on Robotics and …, 2024 - ieeexplore.ieee.org
Understanding how humans leverage semantic knowledge to navigate unfamiliar
environments and decide where to explore next is pivotal for developing robots capable of …

Visual whole-body control for legged loco-manipulation

M Liu, Z Chen, X Cheng, Y Ji, RZ Qiu, R Yang… - arXiv preprint arXiv …, 2024 - arxiv.org
We study the problem of mobile manipulation using legged robots equipped with an arm,
namely legged loco-manipulation. The robot legs, while usually utilized for mobility, offer an …

Umi on legs: Making manipulation policies mobile with manipulation-centric whole-body controllers

H Ha, Y Gao, Z Fu, J Tan, S Song - arXiv preprint arXiv:2407.10353, 2024 - arxiv.org
We introduce UMI-on-Legs, a new framework that combines real-world and simulation data
for quadruped manipulation systems. We scale task-centric data collection in the real world …

Gamma: Graspability-aware mobile manipulation policy learning based on online grasping pose fusion

J Zhang, N Gireesh, J Wang, X Fang… - … on Robotics and …, 2024 - ieeexplore.ieee.org
Mobile manipulation constitutes a fundamental task for robotic assistants and garners
significant attention within the robotics community. A critical challenge inherent in mobile …

Poliformer: Scaling on-policy rl with transformers results in masterful navigators

KH Zeng, Z Zhang, K Ehsani, R Hendrix… - arXiv preprint arXiv …, 2024 - arxiv.org
We present PoliFormer (Policy Transformer), an RGB-only indoor navigation agent trained
end-to-end with reinforcement learning at scale that generalizes to the real-world without …

Adaptive mobile manipulation for articulated objects in the open world

H Xiong, R Mendonca, K Shaw, D Pathak - arXiv preprint arXiv …, 2024 - arxiv.org
Deploying robots in open-ended unstructured environments such as homes has been a long-
standing research problem. However, robots are often studied only in closed-off lab settings …