Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions

Modern nonlinear control theory seeks to develop feedback controllers that endow systems with properties such as safety and stability. The guarantees ensured by these controllers often rely on accurate estimates of the system state for determining control actions. In practice, measurement model uncertainty can lead to error in state estimates that degrades these guarantees. In this paper, we seek to unify techniques from control theory and machine learning to synthesize controllers that achieve safety in the presence of measurement model uncertainty. We define the notion of a Measurement-Robust Control Barrier Function (MR-CBF) as a tool for determining safe control inputs when facing measurement model uncertainty. Furthermore, MR-CBFs are used to inform sampling methodologies for learning-based perception systems and quantify tolerable error in the resulting learned models. We demonstrate the efficacy of MR-CBFs in achieving safety with measurement model uncertainty on a simulated Segway system.

[1]  Simon Lacroix,et al.  On learning visual odometry errors , 2019 .

[2]  Paulo Tabuada,et al.  Control Barrier Functions: Theory and Applications , 2019, 2019 18th European Control Conference (ECC).

[3]  Magnus Egerstedt,et al.  Boolean Composability of Constraints and Control Synthesis for Multi-Robot Systems via Nonsmooth Control Barrier Functions , 2018, 2018 IEEE Conference on Control Technology and Applications (CCTA).

[4]  Petter Nilsson,et al.  Realizable Set Invariance Conditions for Cyber-Physical Systems , 2019, 2019 American Control Conference (ACC).

[5]  Bahram Ravani,et al.  An overview of robot calibration , 1987, IEEE Journal on Robotics and Automation.

[6]  Benjamin Recht,et al.  Certainty Equivalent Perception-Based Control , 2020, ArXiv.

[7]  Yisong Yue,et al.  Learning for Safety-Critical Control with Control Barrier Functions , 2019, L4DC.

[8]  Koushil Sreenath,et al.  Exponential Control Barrier Functions for enforcing high relative-degree safety-critical constraints , 2016, 2016 American Control Conference (ACC).

[9]  Nikolai Matni,et al.  Robust Guarantees for Perception-Based Control , 2019, L4DC.

[10]  L. Perko.  Differential Equations and Dynamical Systems , 1991 .

[11]  Aaron D. Ames,et al.  A Control Barrier Perspective on Episodic Learning via Projection-to-State Safety , 2021, IEEE Control Systems Letters.

[12]  Andrew Clark,et al.  Control Barrier Functions for Complete and Incomplete Information Stochastic Systems , 2019, 2019 American Control Conference (ACC).

[13]  Aaron D. Ames,et al.  Towards a Framework for Realizable Safety Critical Control through Active Set Invariance , 2018, 2018 ACM/IEEE 9th International Conference on Cyber-Physical Systems (ICCPS).

[14]  Dimos V. Dimarogonas,et al.  Learning Control Barrier Functions from Expert Demonstrations , 2020, 2020 59th IEEE Conference on Decision and Control (CDC).

[15]  Martin Connors,et al.  Optimization Models , 2014 .

[16]  Paulo Tabuada,et al.  Robustness of Control Barrier Functions for Safety Critical Control , 2016, ADHS.

[17]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[18]  Petter Nilsson,et al.  Lyapunov-Like Conditions for Tight Exit Probability Bounds through Comparison Theorems for SDEs , 2020, 2020 American Control Conference (ACC).

[19]  Stephen P. Boyd,et al.  ECOS: An SOCP solver for embedded systems , 2013, 2013 European Control Conference (ECC).

[20]  Byron Boots,et al.  Accelerating Imitation Learning with Predictive Models , 2018, AISTATS.

[21]  Alexey Dosovitskiy,et al.  End-to-End Driving Via Conditional Imitation Learning , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[22]  Aaron D. Ames,et al.  An Online Approach to Active Set Invariance , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[23]  Koushil Sreenath,et al.  Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions , 2020, Robotics: Science and Systems.

[24]  Gábor Orosz,et al.  End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks , 2019, AAAI.

[25]  Byron Boots,et al.  Deep Forward and Inverse Perceptual Models for Tracking and Prediction , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[26]  Claire Tomlin,et al.  Eyes-Closed Safety Kernels: Safety for Autonomous Systems Under Loss of Observability , 2020, Robotics: Science and Systems.

[27]  Masaki Yamakita,et al.  Robust Constrained Stabilization Control Using Control Lyapunov and Control Barrier Function in the Presence of Measurement Noises , 2018, 2018 IEEE Conference on Control Technology and Applications (CCTA).

[28]  Vijay Kumar,et al.  Aggressive Flight With Suspended Payloads Using Vision-Based Control , 2018, IEEE Robotics and Automation Letters.

[29]  Paulo Tabuada,et al.  Control barrier function based quadratic programs with application to adaptive cruise control , 2014, 53rd IEEE Conference on Decision and Control.

[30]  Aaron D. Ames,et al.  Control Barrier Functions for Sampled-Data Systems with Input Delays , 2020, 2020 59th IEEE Conference on Decision and Control (CDC).

[31]  Paulo Tabuada,et al.  Control Barrier Function Based Quadratic Programs for Safety Critical Systems , 2016, IEEE Transactions on Automatic Control.

[32]  W. Hager,et al.  Lipschitzian stability in nonlinear control and optimization , 1993 .

[33]  Mrdjan Jankovic,et al.  Robust control barrier functions for constrained stabilization of nonlinear systems , 2018, Autom..

[34]  Boris S. Mordukhovich,et al.  Full Stability of Locally Optimal Solutions in Second-Order Cone Programs , 2014, SIAM J. Optim..

[35]  Franco Blanchini,et al.  Set invariance in control , 1999, Autom..