10 citations · 10 across the 3 of their papers we have counts for
10 papers · 1 filter
CLAMGen: Closed-Loop Arm Motion Generation via Multi-view Vision-Based RL
Iretiayo Akinola, Zizhao Wang, Peter Allen
We propose a vision-based reinforcement learning (RL) approach for closed-loop trajectory generation in an arm reaching problem. Arm trajectory generation is a fundamental robotics…
Dynamic Grasping with Reachability and Motion Awareness
Iretiayo Akinola, Jingxi Xu, Shuran Song +1
Grasping in dynamic environments presents a unique set of challenges. A stable and reachable grasp can become unreachable and unstable as the target object moves, motion planning n…
Maximizing BCI Human Feedback using Active Learning
Zizhao Wang, Junyao Shi, Iretiayo Akinola +1
Recent advancements in \textit{Learning from Human Feedback} present an effective way to train robot agents via inputs from non-expert humans, without a need for a specially design…
SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Tasks
Bohan Wu, Feng Xu, Zhanpeng He +2
Recent advances in deep reinforcement learning (RL) have demonstrated its potential to learn complex robotic manipulation tasks. However, RL still requires the robot to collect a l…
MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning
Bohan Wu, Iretiayo Akinola, Jacob Varley +1
Vision-based grasping systems typically adopt an open-loop execution of a planned grasp. This policy can fail due to many reasons, including ubiquitous calibration error. Recovery…
Accelerated Robot Learning via Human Brain Signals
Iretiayo Akinola, Zizhao Wang, Junyao Shi +6
In reinforcement learning (RL), sparse rewards are a natural way to specify the task to be learned. However, most RL algorithms struggle to learn in this setting since the learning…