Human-Robot Collaboration via Deep Reinforcement Learning of Real-World Interactions
This work addresses the challenge of human-robot collaboration for robotics and AI applications, but it appears incremental as it builds on existing deep learning methods to advance collaborative learning.
The paper tackled the problem of enabling robots to learn collaborative tasks with humans in real-world settings, achieving this by implementing a robotic platform that learned a non-trivial task with a human partner using only 30 minutes of real-world interactions without simulation pre-training.
We present a robotic setup for real-world testing and evaluation of human-robot and human-human collaborative learning. Leveraging the sample-efficiency of the Soft Actor-Critic algorithm, we have implemented a robotic platform able to learn a non-trivial collaborative task with a human partner, without pre-training in simulation, and using only 30 minutes of real-world interactions. This enables us to study Human-Robot and Human-Human collaborative learning through real-world interactions. We present preliminary results, showing that state-of-the-art deep learning methods can take human-robot collaborative learning a step closer to that of humans interacting with each other.