A survey of robot learning from demonstrations for Human-Robot Collaboration

By Jangwon Lee. 2017

232 citations recorded by the source corpus.

Robot learning from demonstration (LfD) is a research paradigm that can play an important role in addressing the issue of scaling up robot learning. Since this type of approach enables non-robotics experts can teach robots new knowledge without any professional background of mechanical engineering or computer programming skills, robots can appear in the real world even if it does not have any prior knowledge for any tasks like a new born baby. There is a growing body of literature that employ LfD approach for training robots. In this paper, I present a survey of recent research in this area while focusing on studies for human-robot collaborative tasks. Since there are different aspects between stand-alone tasks and collaborative tasks, researchers should consider these differences to design collaborative robots for more effective and natural human-robot collaboration (HRC). In this regard, many researchers have shown an increased interest in to make better communication framework between robots and humans because communication is a key issue to apply LfD paradigm for human-robot collaboration. I thus review some recent works that focus on designing better communication channels/methods at the first, then deal with another interesting research method, Interactive/Active learning, after that I finally present other recent approaches tackle a more challenging problem, learning of complex tasks, in the last of the paper.

Subfields: Artificial Intelligence, Control and Systems Engineering, Mechanical Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

In Mechanical Engineering

Citations in the corpus

Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation (2018, background): “…(LfD) data collection strategies are present in literature, we select two ways of capturing demonstrations: (a) Kinesthetic Demonstrations [10]: a kinesthetic method for collecting demonstrations since it allows a human demonstrator to both express their desired motion as well as stay in…”
Efficiently Guiding Imitation Learning Algorithms with Human Gaze (2020, methodology): “Imitation learning (IL) (Schaal 1997),(Argall et al. 2009) is an alternative methodology to infer an optimal policy from demonstrations.”
Recent Advancements in End-to-End Autonomous Driving Using Deep Learning: A Survey (2023, methodology): “[29] trained an End-to-End convolutional neural network for obstacle avoidance using input from a stereo camera, and the training was based on imitation learning through demonstrations.”
The NetHack Learning Environment (2020, unknown): “Lastly, NetHack can also drive research on learning from demonstrations [1, 3] since a large collection of replay data is available.”
Emergent Social Learning via Multi-agent Reinforcement Learning (2020, unknown): “There is a rich body of work on imitation learning, which focuses on training an agent to closely approximate the behavior of a curated set of expert trajectories (Pomerleau, 1989; Schaal, 1999; Billard et al., 2008; Argall et al., 2009).”
Learning position and orientation dynamics from demonstrations via contraction analysis (2018, methodology): “LfD is a widely used approach for imitation learning, in which a new task or skill is learned from demonstrations provided by humans [see Argall et al. (2009) for a comprehensive review].”
Reinforcement Learning from Demonstration through Shaping (2015, unknown): “A lot of other research considering the intersection of LfD and RL focusses on learning a model of the environment (and possibly a reward function), and using RL on simulated experiences in that model to build a good policy [Abbeel and Ng, 2005; Argall et al., 2009] .”
AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos (2019, background): “Our work, in line with robotic imitation learning approaches [1], circumvents the need for a”
Survey on human–robot collaboration in industrial settings: Safety, intuitive interfaces and applications (2018, background): “A complete overview of PbD has been provided in [8], and a full classification can be found in [139].”
Interactively shaping robot behaviour with unlabeled human instructions (2019, unknown): “Several types of teaching signals can be provided, such as demonstrations [1], instructions [35] and evaluative feedback [18].”