We present the Neural Simplex Architecture (NSA), a new approach to runtime assurance that provides safety guarantees for neural controllers (obtained e.g. using reinforcement learning) of autonomous and other complex systems without unduly sacrificing performance. NSA is inspired by the Simplex control architecture of Sha et al., but with some significant differences. In the traditional approach, the advanced controller (AC) is treated as a black box; when the decision module switches control to the baseline controller (BC), the BC remains in control forever. There is relatively little work on switching control back to the AC, and there are no techniques for correcting the AC's behavior after it generates a potentially unsafe control input that causes a failover to the BC. Our NSA addresses both of these limitations. NSA not only provides safety assurances in the presence of a possibly unsafe neural controller, but can also improve the safety of such a controller in an online setting via retraining, without overly degrading its performance. To demonstrate NSA's benefits, we have conducted several significant case studies in the continuous control domain. These include a targetseeking ground rover navigating an obstacle field, and a neural controller for an artificial pancreas system.

We introduce the State Classification Problem (SCP) for hybrid systems, and present Neural State Classification (NSC) as an efficient solution technique. SCP generalizes the model checking problem as it entails classifying each state s of a hybrid automaton as either positive or negative, depending on whether or not s satisfies a given time-bounded reachability specification. This is an interesting problem in its own right, which NSC solves using machine-learning techniques, Deep Neural Networks in particular. State classifiers produced by NSC tend to be very efficient (run in constant time and space), but may be subject to classification errors. To quantify and mitigate such errors, our approach comprises: i) techniques for certifying, with statistical guarantees, that an NSC classifier meets given accuracy levels; ii) tuning techniques, including a novel technique based on adversarial sampling, that can virtually eliminate false negatives (positive states classified as negative), thereby making the classifier more conservative. We have applied NSC to six nonlinear hybrid system benchmarks, achieving an accuracy of 99.25% to 99.98%, and a false-negative rate of 0.0033 to 0, which we further reduced to 0.0015 to 0 after tuning the classifier. We believe that this level of accuracy is acceptable in many practical applications, and that these results demonstrate the promise of the NSC approach. arXiv:1807.09901v1 [cs.LG] 26 Jul 2018We call such a function a state classifier. SCP generalizes the model checking problem. Model checking, in the context of SCP, is simply the problem of determining whether there exists a positive state in the set of initial states. Its intent is not to classify all states in S.Classifying the states of a complex system is an interesting problem in its own right. State classification is also useful in at least two other contexts. First, due to random disturbances, a hybrid system may restart in a random state outside the initial region, and we may wish to check the system's safety from that state. Secondly, a classifier can be used for online model checking [26], where in the process of monitoring a system's behavior, one would like to determine, in real-time, the fate of the system going forward from the current (non-initial) state.This paper shows how deep neural networks (DNNs) can be used for state classification, an approach we refer to as Neural State Classification (NSC). An NSC classifier is subject to false positives (FPs) -a state s is deemed positive when it is actually negative, and, more importantly, false negatives (FNs)s is deemed negative when it is actually positive.A well-trained NSC classifier offers high accuracy, runs in constant time (approximately 1 millisecond, in our experiments), and takes constant space (e.g., a DNN with l hidden layers and n neurons only requires functions of dimension l · n for its encoding). This makes NSC classifiers very appealing for applications such as online model checking, a type of analysis subject to strict time and space constraints...

The popularity of rule-based flocking models, such as Reynolds' classic flocking model, raises the question of whether more declarative flocking models are possible. This question is motivated by the observation that declarative models are generally simpler and easier to design, understand, and analyze than operational models. We introduce a very simple control law for flocking based on a cost function capturing cohesion (agents want to stay together) and separation (agents do not want to get too close). We refer to it as declarative flocking (DF). We use model-predictive control (MPC) to define controllers for DF in centralized and distributed settings. A thorough performance comparison of our declarative flocking with Reynolds' classic flocking model, and with more recent flocking models that use MPC with a cost function based on lattice structures, demonstrate that DF-MPC yields the best cohesion and least fragmentation, and maintains a surprisingly good level of geometric regularity while still producing natural flock shapes similar to those produced by Reynolds' model. We also show that DF-MPC has high resilience to sensor noise. ACM Reference Format:

Abstract. This paper addresses the problem of safely navigating a mobile robot with limited sensing capability and limited information about stationary obstacles. We consider two sensing limitations: blind spots between sensors and limited sensing range. We identify a set of constraints on the sensors' readings whose satisfaction at time t guarantees collisionfreedom during the time interval [t, t+∆t]. Here, ∆t is a parameter whose value is bounded by a function of the maximum velocity of the robot and the range of the sensors. The constraints are obtained under assumptions about minimum internal angle and minimum edge length of polyhedral obstacles. We apply these constraints in the switching logic of the Simplex architecture to obtain a controller that ensures collision-freedom. Experiments we have conducted are consistent with these claims. To the best of our knowledge, our study is the first to provide runtime assurance that an autonomous mobile robot with limited sensing can navigate without collisions with only limited information about obstacles.

We present Component-Based Simplex Architecture (CBSA), a new framework for assuring the runtime safety of component-based cyber-physical systems (CPSs). CBSA integrates Assume-Guarantee (A-G) reasoning with the core principles of the Simplex control architecture to allow component-based CPSs to run advanced, uncertified controllers while still providing runtime assurance that A-G contracts and global properties are satisfied. In CBSA, multiple Simplex instances, which can be composed in a nested, serial or parallel manner, coordinate to assure system-wide properties.Combining A-G reasoning and the Simplex architecture is a challenging problem that yields significant benefits. By utilizing A-G contracts, we are able to compositionally determine the switching logic for CBSAs, thereby alleviating the state explosion encountered by other approaches. Another benefit is that we can use A-G proof rules to decompose the proof of system-wide safety assurance into sub-proofs corresponding to the componentbased structure of the system architecture. We also introduce the notion of coordinated switching between Simplex instances, a key component of our compositional approach to reasoning about CBSA switching logic.We illustrate our framework with a component-based control system for a ground rover. We formally prove that the CBSA for this system guarantees energy safety (the rover never runs out of power), and collision freedom (the rover never collides with a stationary obstacle). We also consider a CBSA for the rover that guarantees mission completion: all target destinations visited within a prescribed amount of time.