Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952366022> ?p ?o ?g. }
- W2952366022 abstract "Model predictive control (MPC) is an effective method for controlling robotic systems, particularly autonomous aerial vehicles such as quadcopters. However, application of MPC can be computationally demanding, and typically requires estimating the state of the system, which can be challenging in complex, unstructured environments. Reinforcement learning can in principle forego the need for explicit state estimation and acquire a policy that directly maps sensor readings to actions, but is difficult to apply to unstable systems that are liable to fail catastrophically during training before an effective policy has been found. We propose to combine MPC with reinforcement learning in the framework of guided policy search, where MPC is used to generate data at training time, under full state observations provided by an instrumented training environment. This data is used to train a deep neural network policy, which is allowed to access only the raw observations from the vehicle's onboard sensors. After training, the neural network policy can successfully control the robot without knowledge of the full state, and at a fraction of the computational cost of MPC. We evaluate our method by learning obstacle avoidance policies for a simulated quadrotor, using simulated onboard sensors and no explicit state estimation at test time." @default.
- W2952366022 created "2019-06-27" @default.
- W2952366022 creator A5026322200 @default.
- W2952366022 creator A5034291270 @default.
- W2952366022 creator A5049349154 @default.
- W2952366022 creator A5064156720 @default.
- W2952366022 date "2015-09-22" @default.
- W2952366022 modified "2023-09-26" @default.
- W2952366022 title "Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search" @default.
- W2952366022 cites W1520597402 @default.
- W2952366022 cites W1570233100 @default.
- W2952366022 cites W1576721254 @default.
- W2952366022 cites W1605218591 @default.
- W2952366022 cites W1665214252 @default.
- W2952366022 cites W1704276703 @default.
- W2952366022 cites W1757796397 @default.
- W2952366022 cites W195033972 @default.
- W2952366022 cites W1969705022 @default.
- W2952366022 cites W1977655452 @default.
- W2952366022 cites W1980969546 @default.
- W2952366022 cites W1981723834 @default.
- W2952366022 cites W2007726556 @default.
- W2952366022 cites W2012587148 @default.
- W2952366022 cites W2028893450 @default.
- W2952366022 cites W2035734362 @default.
- W2952366022 cites W2051620263 @default.
- W2952366022 cites W2062731992 @default.
- W2952366022 cites W2087387266 @default.
- W2952366022 cites W2087617385 @default.
- W2952366022 cites W2091219706 @default.
- W2952366022 cites W2104733512 @default.
- W2952366022 cites W2109008048 @default.
- W2952366022 cites W2121103318 @default.
- W2952366022 cites W2125612430 @default.
- W2952366022 cites W2126909264 @default.
- W2952366022 cites W2139053308 @default.
- W2952366022 cites W2147032798 @default.
- W2952366022 cites W2150930292 @default.
- W2952366022 cites W2155007355 @default.
- W2952366022 cites W2156377376 @default.
- W2952366022 cites W2158782408 @default.
- W2952366022 cites W2161395589 @default.
- W2952366022 cites W2167224731 @default.
- W2952366022 cites W2167562394 @default.
- W2952366022 cites W2169209873 @default.
- W2952366022 cites W2281096776 @default.
- W2952366022 cites W2591436094 @default.
- W2952366022 cites W2962957031 @default.
- W2952366022 cites W2964121744 @default.
- W2952366022 cites W658381347 @default.
- W2952366022 doi "https://doi.org/10.48550/arxiv.1509.06791" @default.
- W2952366022 hasPublicationYear "2015" @default.
- W2952366022 type Work @default.
- W2952366022 sameAs 2952366022 @default.
- W2952366022 citedByCount "14" @default.
- W2952366022 countsByYear W29523660222016 @default.
- W2952366022 countsByYear W29523660222017 @default.
- W2952366022 countsByYear W29523660222018 @default.
- W2952366022 countsByYear W29523660222019 @default.
- W2952366022 countsByYear W29523660222020 @default.
- W2952366022 crossrefType "posted-content" @default.
- W2952366022 hasAuthorship W2952366022A5026322200 @default.
- W2952366022 hasAuthorship W2952366022A5034291270 @default.
- W2952366022 hasAuthorship W2952366022A5049349154 @default.
- W2952366022 hasAuthorship W2952366022A5064156720 @default.
- W2952366022 hasBestOaLocation W29523660221 @default.
- W2952366022 hasConcept C108583219 @default.
- W2952366022 hasConcept C11413529 @default.
- W2952366022 hasConcept C119857082 @default.
- W2952366022 hasConcept C127413603 @default.
- W2952366022 hasConcept C133731056 @default.
- W2952366022 hasConcept C154945302 @default.
- W2952366022 hasConcept C172205157 @default.
- W2952366022 hasConcept C17744445 @default.
- W2952366022 hasConcept C199539241 @default.
- W2952366022 hasConcept C19966478 @default.
- W2952366022 hasConcept C2775924081 @default.
- W2952366022 hasConcept C2776650193 @default.
- W2952366022 hasConcept C34413123 @default.
- W2952366022 hasConcept C41008148 @default.
- W2952366022 hasConcept C48103436 @default.
- W2952366022 hasConcept C50644808 @default.
- W2952366022 hasConcept C6683253 @default.
- W2952366022 hasConcept C90509273 @default.
- W2952366022 hasConcept C97541855 @default.
- W2952366022 hasConceptScore W2952366022C108583219 @default.
- W2952366022 hasConceptScore W2952366022C11413529 @default.
- W2952366022 hasConceptScore W2952366022C119857082 @default.
- W2952366022 hasConceptScore W2952366022C127413603 @default.
- W2952366022 hasConceptScore W2952366022C133731056 @default.
- W2952366022 hasConceptScore W2952366022C154945302 @default.
- W2952366022 hasConceptScore W2952366022C172205157 @default.
- W2952366022 hasConceptScore W2952366022C17744445 @default.
- W2952366022 hasConceptScore W2952366022C199539241 @default.
- W2952366022 hasConceptScore W2952366022C19966478 @default.
- W2952366022 hasConceptScore W2952366022C2775924081 @default.
- W2952366022 hasConceptScore W2952366022C2776650193 @default.
- W2952366022 hasConceptScore W2952366022C34413123 @default.
- W2952366022 hasConceptScore W2952366022C41008148 @default.
- W2952366022 hasConceptScore W2952366022C48103436 @default.