Recent Advances in Robot Learning from Demonstration

By Harish Chaandar Ravichandar, Athanasios S. Polydoros, Sonia Chernova, Aude Gemma Billard. 2020

877 citations recorded by the source corpus.

In the context of robotics and automation, learning from demonstration (LfD) is the paradigm in which robots acquire new skills by learning to imitate an expert. The choice of LfD over other robot learning methods is compelling when ideal behavior can be neither easily scripted (as is done in traditional robot programming) nor easily defined as an optimization problem, but can be demonstrated. While there have been multiple surveys of this field in the past, there is a need for a new one given the considerable growth in the number of publications in recent years. This review aims to provide an overview of the collection of machine-learning methods used to enable a robot to learn from and imitate a teacher. We focus on recent advancements in the field and present an updated taxonomy and characterization of existing methods. We also discuss mature and emerging application areas for LfD and highlight the significant challenges that remain to be overcome both in theory and in practice.

Subfields: Artificial Intelligence, Control and Systems 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

Citations in the corpus

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning (2020, methodology): “Data-driven algorithms [9], such as reinforcement learning [13, 7] and imitation learning [12], provide a powerful and generic tool in robotics.”
Voyager: An Open-Ended Embodied Agent with Large Language Models (2023, background): “[77] Harish Ravichandar, Athanasios S Polydoros, Sonia Chernova, and Aude Billard.”
Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning (2021, background): “Previous review works focused on specific techniques—for example, learning-based model predictive control (MPC) (7), iterative learning control (ILC) (8, 9), model-based RL (10), data-efficient policy search (11), imitation learning (12), or the use of RL in robotics (13, 14) and in optimal control ”
Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots (2024, methodology): “To ensure model capacity, we increased the vision encoder further to CLIP [30] pretrained ViT-L/14 [11].”
VIMA: General Robot Manipulation with Multimodal Prompts (2022, neutral): “Embodied agent research (Duan et al., 2022; Batra et al., 2020; Ravichandar et al., 2020; Collins et al., 2021) is adopting the large-scale pre-training paradigm (Yang et al., 2023), powered by a collection of learning environments (Abramson et al., 2020; Shridhar et al., 2020; Savva et al., 2019;…”
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge (2022, neutral): “Inspired by the success in NLP, embodied agent research [29, 11, 94, 23] has seen a surge in adoption of the large-scale pre-training paradigm.”
Diffusion policy: Visuomotor policy learning via action diffusion (2023, background): “Creating capable robots without requiring explicit programming of behaviors is a longstanding challenge in the field [3, 2, 38].”
A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges (2023, neutral): “These methods demanded intricate, handcrafted rules dictating the actions of machines, and the dynamics of their operating environments, requiring signiﬁcant time and coding expertise [2].”