[go: up one dir, main page]

Sun et al., 2021 - Google Patents

Provably correct training of neural network controllers using reachability analysis

Sun et al., 2021

View PDF
Document ID
11350579171153353273
Author
Sun X
Shoukry Y
Publication year
Publication venue
arXiv preprint arXiv:2102.10806

External Links

Snippet

In this paper, we consider the problem of training neural network (NN) controllers for nonlinear dynamical systems that are guaranteed to satisfy safety and liveness (eg, reach- avoid) properties. Our approach is to combine model-based design methodologies for …
Continue reading at arxiv.org (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/04—Architectures, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass
    • G06N99/005—Learning machines, i.e. computer in which a programme is changed according to experience gained by the machine itself during a complete run
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B17/00—Systems involving the use of models or simulators of said systems
    • G05B17/02—Systems involving the use of models or simulators of said systems electric
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models
    • G06N5/04—Inference methods or devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models
    • G06N5/02—Knowledge representation
    • G06N5/022—Knowledge engineering, knowledge acquisition
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/39—Robotics, robotics to robotics hand
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6267—Classification techniques
    • G06K9/6279—Classification techniques relating to the number of classes

Similar Documents

Publication Publication Date Title
Hu et al. Reach-sdp: Reachability analysis of closed-loop systems with neural network controllers via semidefinite programming
Taylor et al. Episodic learning with control lyapunov functions for uncertain robotic systems
Dean et al. Robust guarantees for perception-based control
Chen et al. Approximating explicit model predictive control using constrained neural networks
Kamalapurkar et al. Reinforcement learning for optimal feedback control
Lechner et al. Stability verification in stochastic control systems via neural network supermartingales
Oshin et al. Differentiable robust model predictive control
Sun et al. Provably correct training of neural network controllers using reachability analysis
Li et al. Neural networks for cooperative control of multiple robot arms
Günther Machine intelligence for adaptable closed loop and open loop production engineering systems
Chen et al. Safety filter design for neural network systems via convex optimization
Di Natale et al. Simba: System identification methods leveraging backpropagation
Wang et al. Deep bilinear Koopman realization for dynamics modeling and predictive control
Potteiger et al. Safe explainable agents for autonomous navigation using evolving behavior trees
Valadas et al. Learning low-dimensional strain models of soft robots by looking at the evolution of their shape with application to model-based control
Idoko et al. Learning sampling distribution and safety filter for autonomous driving with vq-vae and differentiable optimization
Lozenguez On the distributivity of multi-agent markov decision processes for mobile-robotics
Cubuktepe et al. Shared control with human trust and workload models
Da Silva et al. Data driven state reconstruction of dynamical system based on approximate dynamic programming and reinforcement learning
Poonawala et al. Training classifiers for feedback control
Hassan Tube-based NMPC for Non-Holonomic
Lopez et al. Decomposing control lyapunov functions for efficient reinforcement learning
Gah et al. Closed loop intent-expressive trajectory planning and intent estimation
Yuan et al. Multi-expert synthesis for versatile locomotion and manipulation skills
Csomay-Shanklin Layered Control Architectures: Constructive Theory and Application to Legged Robots