Autonomous Helicopter Aerobatics through Apprenticeship Learning

By Pieter Abbeel, Adam Coates, Andrew Y. Ng. 2010

677 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition, Reinforcement Learning

How researchers see this paper

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

In Aerospace Engineering

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Reinforcement Learning

Citations in the corpus

Learning Trajectory Preferences for Manipulators via Iterative Improvement (2013, background): “Most of the past research has focused on mimicking expert’s demonstrations, for example, autonomous helicopter flights [1], ball-in-a-cup experiment [17], planning 2-D paths [27, 25, 26], etc.”
End-to-End Driving Via Conditional Imitation Learning (2017, background): “Imitation learning has been applied to a variety of tasks, including articulated motion [2], [28], [11], autonomous flight [1], [13], [30], modeling navigational behavior [37], [38], off-road driving [22], [32], and road following [4], [6], [27], [36].”
ROBOTURK: A Crowdsourcing Platform for Robotic Skill Learning through Imitation (2018, methodology): “Prior works show that data-driven IL methods improve both the sample efﬁciency of policy learning [16, 17, 18] and the performance of the trained policy [19, 20, 21].”
Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation (2017, background): “It is straightforward to obtain human demonstrations for car driving [4], [5] or RC helicopter ﬂight [7], because existing control interfaces allow human operators to perform sophisticated, high-quality maneuvers in these domains easily.”
Third-Person Imitation Learning (2017, background): “This reward function could be represented as nearness to a trajectory (Calinon et al., 2007; Abbeel et al., 2010), as a weighted combination of features (Abbeel & Ng, 2004; Ratliff et al., 2006; Ramachandran & Amir, 2007; Ziebart et al., 2008; Boularias et al., 2011; Kalakrishnan et al., 2013;…”
An Algorithmic Perspective on Imitation Learning (2018, methodology): “Meanwhile, an iterative LQR controller for the lower-level control in [Abbeel et al., 2010] can be considered as a feedback policy because it determines the control input based on the observation of the system.”
Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-to-End Learning from Demonstration (2017, methodology): “In recent years, LfD was successfully used in the field of robotics for applications as varied as autonomous helicopter maneuvers [1], playing table tennis [2], object manipulation [3], making coffee [4], grasping novel objects [5], carrot grating [6], and eggplant cutting [7].”
AI Safety Gridworlds (2017, background): “Another possible avenue could be the use of prior information, for example through imitation learning (Abbeel et al., 2010; Santara et al., 2017): the agent could try to “stay close” to the state space covered by demonstrations pro-”
Inverse Reinforcement Learning in Swarm Systems (2016, methodology): “only relative angles between the agents. Finally, we compare the results in terms of the order parameter [30], which provides a measure for the total alignment of the swarm, ! t:= 1 Nv t XN n=1 v(n) 2[0;1]; with values close to 1 indicating strong synchronization of the system. Figure 6 depicts its ”
A Divergence Minimization Perspective on Imitation Learning Methods (2019, background): “Inverse Reinforcement Learning (IRL) algorithms have shown promising results in challenging continuous control problems [29, 30, 2, 1, 7], outperforming BC. Similarly to RL, the connections between IRL and divergence minimization have long been alluded.”
Exploration from Demonstration for Interactive Reinforcement Learning (2016, background): “…successful at solving a variety of problems like computer games (Backgammon [39], Atari games [26]), robot tasks (soccer [34], helicopter control [1]) and system operations (inventory management [16]); however, in general, standard RL approaches do not scale well with the size of the problem and…”
Information theoretic MPC for model-based reinforcement learning (2017, methodology): “In the second paradigm, model-based RL approaches first learn a model of the system and then train a feedback control policy using the learned model [6]–[8].”
Alignment for Advanced Machine Learning Systems (2020, methodology): “Inverse reinforcement learning methods have been successfully applied to autonomous helicopter control, achieving human-level performance (Abbeel, Coates, and Ng 2010), and have recently been extended to the learning of non-linear cost features in the environment, producing good results in robotic…”
Interaction primitives for human-robot cooperation tasks (2014, methodology): “Imitation learning has been successfully used to learn a wide range of tasks in robotics [2], such as basic robot walking [4], [5], driving robot cars [10], object manipulation [9], and helicopter manoeuvring [1].”
Automatic re-initialization and failure recovery for aggressive flight with a monocular vision-based quadrotor (2015, background): “Autonomous Micro Aerial Vehicles (MAVs) will soon play a major role in remote inspection and search-andrescue missions.”