Autonomous Helicopter Flight via Reinforcement Learning

By Andrew Y. Ng, H. Jin Kim, Michael I. Jordan, S. Sastry. 2003

377 citations recorded by the source corpus.

How researchers see this paper

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

In Reinforcement Learning

Citations in the corpus

One-Shot Imitation Learning (2017, background): “Reinforcement learning has had many successes, including Backgammon [57], helicopter control [39], Atari [35], Go [52], continuous control in simulation [51, 21, 32] and on real robots [40, 30].”
Reinforcement learning in robotics: A survey (2013, methodology): “Figure 7: Autonomous inverted helicopter flight (Ng et al., 2004b)(Picture reprint with permission of Andrew Ng).”
Target-driven visual navigation in indoor scenes using deep reinforcement learning (2016, neutral): “[28] apply reinforcement learning to autonomous helicopter flight.”
Cognitive Mapping and Planning for Visual Navigation (2017, methodology): “As an alternative to separating out discrete mapping and planning phases, reinforcement learning (RL) methods directly learn policies for robotic tasks (Kim et al. 2003; Peters and Schaal 2008; Kohl and Stone 2004).”
Visual Semantic Planning Using Deep Successor Representations (2017, methodology): “To address the second and third challenges, we cast VSP as a policy learning problem, typically tackled by reinforcement learning [11, 16, 22, 30, 35, 46].”
The dynamics of perception and action. (2006, methodology): “Indeed, using a method such as reinforcement learning (Kaelbling, Littman, & Moore, 1996; Sutton & Barto, 1998) to acquire a sensor–effector mapping that exploits the natural dynamics can yield stable movement patterns without explicit internal models (Berthier et al,, 2005; Collins, Ruina, Tedrake,”
Gaussian Processes and Reinforcement Learning for Identification and Control of an Autonomous Blimp (2007, background): “Artificial Neural Networks (ANNs) are often chosen as a basis for controller design [11].”
RTMBA: A Real-Time Model-Based Reinforcement Learning Architecture for robot control (2011, methodology): “RL has been applied to a few carefully chosen robotic tasks that are achievable with limited training and infrequent action selections [2], or allow for an off-line learning phase [3].”
Deep auto-encoder neural networks in reinforcement learning (2010, methodology): “Select an action at ← πk(zt) and store the completed transition in observation space O: FO ← FO ∪ (op, ap, rp+1, op+1) incrementing p with each observed transition.”
Reinforcement learning improves behaviour from evaluative feedback (2015, methodology): “In applications such as a robot helicopter learning acrobatic tricks, experience is slow to collect and there is ample time offline to compute decision policies, making a model-based approach appropriate 29 .”
Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not (2016, background): “A variety of robotics control problems are solvable by reinforcement learning, such as inverted helicopter ﬂight learning (Kim et al., 2003; Ng et al., 2006), gliding aircraft control (Chung et al., 2015), mobile robot navigation (Kretzschmar et al., 2016), modular robot control (Varshavskaya et…”