![]() ![]() The control policy is represented by a feedforward neural network and is trained in simulation using model-free on-policy deep RL 31. Swift consists of two key modules: (1) a perception system that translates high-dimensional visual and inertial information into a low-dimensional representation and (2) a control policy that ingests the low-dimensional representation produced by the perception system and produces control commands. In this article, we describe Swift, an autonomous system that can race a quadrotor at the level of human world champions using only onboard sensors and computation. This makes the comparison with human pilots unfair, as humans only have access to onboard observations from the drone. However, these works rely on near-perfect state estimation provided by an external motion-capture system. More recently, autonomous systems have begun to reach expert human performance 28, 29, 30. However, the first two teams still took almost twice as long as a professional human pilot to complete the track 26, 27. The 2019 AlphaPilot autonomous drone racing competition showcased some of the best research in the field 25. A series of innovations followed, including the use of deep networks to identify the next gate location 18, 19, 20, transfer of racing policies from simulation to reality 21, 22 and accounting for uncertainty in perception 23, 24. 1c).Īttempts to create autonomous systems that reach the performance of human pilots date back to the first autonomous drone racing competition in 2016 (ref. Each vehicle is remotely controlled by a human pilot who wears a headset showing a video stream from an onboard camera, creating an immersive ‘first-person-view’ experience (Fig. During a race, the vehicles exert forces that surpass their own weight by a factor of five or more, reaching speeds of more than 100 km h −1 and accelerations several times that of gravity, even in confined spaces. The vehicles used in FPV racing are quadcopters, which are among the most agile machines ever built (Fig. Overcoming this limitation and demonstrating champion-level performance in physical competitions is a long-standing problem in autonomous mobile robotics and artificial intelligence 14, 15, 16.įPV drone racing is a televised sport in which highly trained human pilots push aerial vehicles to their physical limits in high-speed agile manoeuvres (Fig. These impressive demonstrations of the capabilities of machine intelligence have primarily been limited to simulation and board-game environments, which support policy search in an exact replica of the testing conditions. Policies trained with deep RL have outperformed humans in complex competitive games, including Atari 4, 5, 6, Go 5, 7, 8, 9, chess 5, 9, StarCraft 10, Dota 2 (ref. This work represents a milestone for mobile robotics and machine intelligence 2, which may inspire the deployment of hybrid learning-based solutions in other physical systems.ĭeep RL 3 has enabled some recent advances in artificial intelligence. Swift won several races against each of the human champions and demonstrated the fastest recorded race time. Swift competed against three human champions, including the world champions of two international leagues, in real-world head-to-head races. The system combines deep reinforcement learning (RL) in simulation with data collected in the physical world. Here we introduce Swift, an autonomous system that can race physical vehicles at the level of the human world champions. Reaching the level of professional pilots with an autonomous drone is challenging because the robot needs to fly at its physical limits while estimating its speed and location in the circuit exclusively from onboard sensors 1. Each pilot sees the environment from the perspective of their drone by means of video streamed from an onboard camera. ![]() First-person view (FPV) drone racing is a televised sport in which professional competitors pilot high-speed aircraft through a 3D circuit. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |