Searcharxiv⌕ Search

arXiv subjects

Mykel J. Kochenderfer

Publications and source records attributed to Mykel J. Kochenderfer.

At least 199 records · Page 11Linked to original sources

Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration

There has been growing progress on theoretical analyses for provably efficient learning in MDPs with linear function approximation, but much of the existing work has made strong assumptions to enable exploration by conventional exploration frameworks. Typically these assumptions are stronger than what is needed to find good solutions in the batch setting. In this work, we show how under a more standard notion of low inherent Bellman error, typically employed in least-square value iteration-style algorithms, we can provide strong PAC guarantees on learning a near optimal value function provided that the linear space is sufficiently "explorable". We present a computationally tractable algorithm for the reward-free setting and show how it can be used to learn a near optimal policy for any (linear) reward function, which is revealed only once learning has completed. If this reward function is also estimated from the samples gathered during pure exploration, our results also provide same-order PAC guarantees on the performance of the resulting policy for this setting.

cs.LG↗

Runtime Safety Assurance Using Reinforcement Learning

The airworthiness and safety of a non-pedigreed autopilot must be verified, but the cost to formally do so can be prohibitive. We can bypass formal verification of non-pedigreed components by incorporating Runtime Safety Assurance (RTSA) as mechanism to ensure safety. RTSA consists of a meta-controller that observes the inputs and outputs of a non-pedigreed component and verifies formally specified behavior as the system operates. When the system is triggered, a verified recovery controller is deployed. Recovery controllers are designed to be safe but very likely disruptive to the operational objective of the system, and thus RTSA systems must balance safety and efficiency. The objective of this paper is to design a meta-controller capable of identifying unsafe situations with high accuracy. High dimensional and non-linear dynamics in which modern controllers are deployed along with the black-box nature of the nominal controllers make this a difficult problem. Current approaches rely heavily on domain expertise and human engineering. We frame the design of RTSA with the Markov decision process (MDP) framework and use reinforcement learning (RL) to solve it. Our learned meta-controller consistently exhibits superior performance in our experiments compared to our baseline, human engineered approach.

cs.LG↗

Algorithms for Verifying Deep Neural Networks

Deep neural networks are widely used for nonlinear function approximation with applications ranging from computer vision to control. Although these networks involve the composition of simple arithmetic operations, it can be very challenging to verify whether a particular network satisfies certain input-output properties. This article surveys methods that have emerged recently for soundly verifying such properties. These methods borrow insights from reachability analysis, optimization, and search. We discuss fundamental differences and connections between existing algorithms. In addition, we provide pedagogical implementations of existing methods and compare them on a set of benchmark problems.

cs.LG↗

Bayesian Optimized Monte Carlo Planning

Online solvers for partially observable Markov decision processes have difficulty scaling to problems with large action spaces. Monte Carlo tree search with progressive widening attempts to improve scaling by sampling from the action space to construct a policy search tree. The performance of progressive widening search is dependent upon the action sampling policy, often requiring problem-specific samplers. In this work, we present a general method for efficient action sampling based on Bayesian optimization. The proposed method uses a Gaussian process to model a belief over the action-value function and selects the action that will maximize the expected improvement in the optimal action value. We implement the proposed approach in a new online tree search algorithm called Bayesian Optimized Monte Carlo Planning (BOMCP). Several experiments show that BOMCP is better able to scale to large action space POMDPs than existing state-of-the-art tree search solvers.

cs.AI↗

Improved POMDP Tree Search Planning with Prioritized Action Branching

Online solvers for partially observable Markov decision processes have difficulty scaling to problems with large action spaces. This paper proposes a method called PA-POMCPOW to sample a subset of the action space that provides varying mixtures of exploitation and exploration for inclusion in a search tree. The proposed method first evaluates the action space according to a score function that is a linear combination of expected reward and expected information gain. The actions with the highest score are then added to the search tree during tree expansion. Experiments show that PA-POMCPOW is able to outperform existing state-of-the-art solvers on problems with large discrete action spaces.

cs.LG↗

A Maximum Independent Set Method for Scheduling Earth Observing Satellite Constellations

Operating Earth observing satellites requires efficient planning methods that coordinate activities of multiple spacecraft. The satellite task planning problem entails selecting actions that best satisfy mission objectives for autonomous execution. Task scheduling is often performed by human operators assisted by heuristic or rule-based planning tools. This approach does not efficiently scale to multiple assets as heuristics frequently fail to properly coordinate actions of multiple vehicles over long horizons. Additionally, the problem becomes more difficult to solve for large constellations as the complexity of the problem scales exponentially in the number of requested observations and linearly in the number of spacecraft. It is expected that new commercial optical and radar imaging constellations will require automated planning methods to meet stated responsiveness and throughput objectives. This paper introduces a new approach for solving the satellite scheduling problem by generating an infeasibility-based graph representation of the problem and finding a maximal independent set of vertices for the graph. The approach is tested on a scenarios of up to 10,000 requested imaging locations for the Skysat constellation of optical satellites as well as simulated constellations of up to 24 satellites. Performance is compared with contemporary graph-traversal and mixed-integer linear programming approaches. Empirical results demonstrate improvements in both the solution time along with the number of scheduled collections beyond baseline methods. For large problems, the maximum independent set approach is able find a feasible schedule with 8% more collections in 75% less time.

cs.AI↗

Analysis of Fleet Management and Network Design for On-Demand Urban Air Mobility Operations

A significant challenge in estimating operational feasibility of Urban Air Mobility (UAM) missions lies in understanding how choices in design impact the performance of a complex system-of-systems. This work examines the ability of the UAM ecosystem and the operations within it to meet a variety of demand profiles that may emerge in the coming years. We perform a set of simulation driven feasibility and scalability analyses based on UAM operational models with the goal of estimating capacity and throughput for a given set of parameters that represent an operational UAM ecosystem. UAM ecosystem design guidelines, vehicle constraints, and effective operational policies can be drawn from our analysis. Results show that, while critical for enabling UAM, the performance of the UAM ecosystem is robust to variations in ground infrastructure and fleet design decisions, while being sensitive to decisions for fleet and traffic management policies. We show that so long as the ecosystem design parameters for ground infrastructure and fleet design fall within a sensible range, the performance of the UAM ecosystem is affected by the policies used to manage the UAM traffic.

cs.OH↗

Dynamic Multi-Robot Task Allocation under Uncertainty and Temporal Constraints

We consider the problem of dynamically allocating tasks to multiple agents under time window constraints and task completion uncertainty. Our objective is to minimize the number of unsuccessful tasks at the end of the operation horizon. We present a multi-robot allocation algorithm that decouples the key computational challenges of sequential decision-making under uncertainty and multi-agent coordination and addresses them in a hierarchical manner. The lower layer computes policies for individual agents using dynamic programming with tree search, and the upper layer resolves conflicts in individual plans to obtain a valid multi-agent allocation. Our algorithm, Stochastic Conflict-Based Allocation (SCoBA), is optimal in expectation and complete under some reasonable assumptions. In practice, SCoBA is computationally efficient enough to interleave planning and execution online. On the metric of successful task completion, SCoBA consistently outperforms a number of baseline methods and shows strong competitive performance against an oracle with complete lookahead. It also scales well with the number of tasks and agents. We validate our results over a wide range of simulations on two distinct domains: multi-arm conveyor belt pick-and-place and multi-drone delivery dispatch in a city.

cs.RO↗

Directional Primitives for Uncertainty-Aware Motion Estimation in Urban Environments

We can use driving data collected over a long period of time to extract rich information about how vehicles behave in different areas of the roads. In this paper, we introduce the concept of directional primitives, which is a representation of prior information of road networks. Specifically, we represent the uncertainty of directions using a mixture of von Mises distributions and associated speeds using gamma distributions. These location-dependent primitives can be combined with motion information of surrounding vehicles to predict their future behavior in the form of probability distributions. Experiments conducted on highways, intersections, and roundabouts in the Carla simulator, as well as real-world urban driving datasets, indicate that primitives lead to better uncertainty-aware motion estimation.

cs.RO↗

Scalable Autonomous Vehicle Safety Validation through Dynamic Programming and Scene Decomposition

An open question in autonomous driving is how best to use simulation to validate the safety of autonomous vehicles. Existing techniques rely on simulated rollouts, which can be inefficient for finding rare failure events, while other techniques are designed to only discover a single failure. In this work, we present a new safety validation approach that attempts to estimate the distribution over failures of an autonomous policy using approximate dynamic programming. Knowledge of this distribution allows for the efficient discovery of many failure examples. To address the problem of scalability, we decompose complex driving scenarios into subproblems consisting of only the ego vehicle and one other vehicle. These subproblems can be solved with approximate dynamic programming and their solutions are recombined to approximate the solution to the full scenario. We apply our approach to a simple two-vehicle scenario to demonstrate the technique as well as a more complex five-vehicle scenario to demonstrate scalability. In both experiments, we observed an increase in the number of failures discovered compared to baseline approaches.

cs.RO↗

Interpretable Safety Validation for Autonomous Vehicles

An open problem for autonomous driving is how to validate the safety of an autonomous vehicle in simulation. Automated testing procedures can find failures of an autonomous system but these failures may be difficult to interpret due to their high dimensionality and may be so unlikely as to not be important. This work describes an approach for finding interpretable failures of an autonomous system. The failures are described by signal temporal logic expressions that can be understood by a human, and are optimized to produce failures that have high likelihood. Our methodology is demonstrated for the safety validation of an autonomous vehicle in the context of an unprotected left turn and a crosswalk with a pedestrian. Compared to a baseline importance sampling approach, our methodology finds more failures with higher likelihood while retaining interpretability.

cs.RO↗

Scalable Identification of Partially Observed Systems with Certainty-Equivalent EM

System identification is a key step for model-based control, estimator design, and output prediction. This work considers the offline identification of partially observed nonlinear systems. We empirically show that the certainty-equivalent approximation to expectation-maximization can be a reliable and scalable approach for high-dimensional deterministic systems, which are common in robotics. We formulate certainty-equivalent expectation-maximization as block coordinate-ascent, and provide an efficient implementation. The algorithm is tested on a simulated system of coupled Lorenz attractors, demonstrating its ability to identify high-dimensional systems that can be intractable for particle-based approaches. Our approach is also used to identify the dynamics of an aerobatic helicopter. By augmenting the state with unobserved fluid states, a model is learned that predicts the acceleration of the helicopter better than state-of-the-art approaches. The codebase for this work is available at https://github.com/sisl/CEEM.

cs.LG↗

Adaptive Stress Testing without Domain Heuristics using Go-Explore

Recently, reinforcement learning (RL) has been used as a tool for finding failures in autonomous systems. During execution, the RL agents often rely on some domain-specific heuristic reward to guide them towards finding failures, but constructing such a heuristic may be difficult or infeasible. Without a heuristic, the agent may only receive rewards at the time of failure, or even rewards that guide it away from failures. For example, some approaches give rewards for taking more-likely actions, because we want to find more-likely failures. However, the agent may then learn to only take likely actions, and may not be able to find a failure at all. Consequently, the problem becomes a hard-exploration problem, where rewards do not aid exploration. A new algorithm, go-explore (GE), has recently set new records on benchmarks from the hard-exploration field. We apply GE to adaptive stress testing (AST), one example of an RL-based falsification approach that provides a way to search for the most-likely failure scenario. We simulate a scenario where an autonomous vehicle drives while a pedestrian is crossing the road. We demonstrate that GE is able to find failures without domain-specific heuristics, such as the distance between the car and the pedestrian, on scenarios that other RL techniques are unable to solve. Furthermore, inspired by the robustification phase of GE, we demonstrate that the backwards algorithm (BA) improves the failures found by other RL techniques.

cs.LG↗

Towards Recurrent Autoregressive Flow Models

Stochastic processes generated by non-stationary distributions are difficult to represent with conventional models such as Gaussian processes. This work presents Recurrent Autoregressive Flows as a method toward general stochastic process modeling with normalizing flows. The proposed method defines a conditional distribution for each variable in a sequential process by conditioning the parameters of a normalizing flow with recurrent neural connections. Complex conditional relationships are learned through the recurrent network parameters. In this work, we present an initial design for a recurrent flow cell and a method to train the model to match observed empirical distributions. We demonstrate the effectiveness of this class of models through a series of experiments in which models are trained on three complex stochastic processes. We highlight the shortcomings of our current formulation and suggest some potential solutions.

cs.LG↗

Optimal Sequential Task Assignment and Path Finding for Multi-Agent Robotic Assembly Planning

We study the problem of sequential task assignment and collision-free routing for large teams of robots in applications with inter-task precedence constraints (e.g., task $A$ and task $B$ must both be completed before task $C$ may begin). Such problems commonly occur in assembly planning for robotic manufacturing applications, in which sub-assemblies must be completed before they can be combined to form the final product. We propose a hierarchical algorithm for computing makespan-optimal solutions to the problem. The algorithm is evaluated on a set of randomly generated problem instances where robots must transport objects between stations in a "factory "grid world environment. In addition, we demonstrate in high-fidelity simulation that the output of our algorithm can be used to generate collision-free trajectories for non-holonomic differential-drive robots.

cs.RO↗

Active Preference-Based Gaussian Process Regression for Reward Learning

Designing reward functions is a challenging problem in AI and robotics. Humans usually have a difficult time directly specifying all the desirable behaviors that a robot needs to optimize. One common approach is to learn reward functions from collected expert demonstrations. However, learning reward functions from demonstrations introduces many challenges: some methods require highly structured models, e.g. reward functions that are linear in some predefined set of features, while others adopt less structured reward functions that on the other hand require tremendous amount of data. In addition, humans tend to have a difficult time providing demonstrations on robots with high degrees of freedom, or even quantifying reward values for given demonstrations. To address these challenges, we present a preference-based learning approach, where as an alternative, the human feedback is only in the form of comparisons between trajectories. Furthermore, we do not assume highly constrained structures on the reward function. Instead, we model the reward function using a Gaussian Process (GP) and propose a mathematical formulation to actively find a GP using only human preferences. Our approach enables us to tackle both inflexibility and data-inefficiency problems within a preference-based learning framework. Our results in simulations and a user study suggest that our approach can efficiently learn expressive reward functions for robotics tasks.

cs.RO↗

Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic

Maneuvering in dense traffic is a challenging task for autonomous vehicles because it requires reasoning about the stochastic behaviors of many other participants. In addition, the agent must achieve the maneuver within a limited time and distance. In this work, we propose a combination of reinforcement learning and game theory to learn merging behaviors. We design a training curriculum for a reinforcement learning agent using the concept of level-$k$ behavior. This approach exposes the agent to a broad variety of behaviors during training, which promotes learning policies that are robust to model discrepancies. We show that our approach learns more efficient policies than traditional training methods.

cs.AI↗

Guaranteeing Safety for Neural Network-Based Aircraft Collision Avoidance Systems

The decision logic for the ACAS X family of aircraft collision avoidance systems is represented as a large numeric table. Due to storage constraints of certified avionics hardware, neural networks have been suggested as a way to significantly compress the data while still preserving performance in terms of safety. However, neural networks are complex continuous functions with outputs that are difficult to predict. Because simulations evaluate only a finite number of encounters, simulations are not sufficient to guarantee that the neural network will perform correctly in all possible situations. We propose a method to provide safety guarantees when using a neural network collision avoidance system. The neural network outputs are bounded using neural network verification tools like Reluplex and Reluval, and a reachability method determines all possible ways aircraft encounters will resolve using neural network advisories and assuming bounded aircraft dynamics. Experiments with systems inspired by ACAS X show that neural networks giving either horizontal or vertical maneuvers can be proven safe. We explore how relaxing the bounds on aircraft dynamics can lead to potentially unsafe encounters and demonstrate how neural network controllers can be modified to guarantee safety through online costs or lowering alerting cost. The reachability method is flexible and can incorporate uncertainties such as pilot delay and sensor error. These results suggest a method for certifying neural network collision avoidance systems for use in real aircraft.

eess.SY↗