Model-based planners for partially observable problems must accommodate both model uncertainty during planning and goal uncertainty during objective inference. However, model-based planners may be brittle under these types of uncertainty because they rely on an exact model and tend to commit to a single optimal behavior. Inspired by results in the model-free setting, we propose an entropy-regularized model-based planner for partially observable problems. Entropy regularization promotes policy robustness for planning and objective inference by encouraging policies to be no more committed to a single action than necessary. We evaluate the robustness and objective inference performance of entropy-regularized policies in three problem domains. Our results show that entropy-regularized policies outperform non-entropy-regularized baselines in terms of higher expected returns under modeling errors and higher accuracy during objective inference.

For autonomous vehicles to proactively plan safe trajectories and make informed decisions, they must be able to predict the future occupancy states of the local environment. However, common issues with occupancy prediction include predictions where moving objects vanish or become blurred, particularly at longer time horizons. We propose an environment prediction framework that incorporates environment semantics for future occupancy prediction. Our method first semantically segments the environment and uses this information along with the occupancy information to predict the spatiotemporal evolution of the environment. We validate our approach on the real-world Waymo Open Dataset. Compared to baseline methods, our model has higher prediction accuracy and is capable of maintaining moving object appearances in the predictions for longer prediction time horizons.

Perception systems operate as a subcomponent of the general autonomy stack, and perception system designers often need to optimize performance characteristics while maintaining safety with respect to the overall closed-loop system. For this reason, it is useful to distill high-level safety requirements into component-level requirements on the perception system. In this work, we focus on efficiently determining sets of safe perception system performance characteristics given a black-box simulator of the fully-integrated, closed-loop system. We combine the advantages of common black-box estimation techniques such as Gaussian processes and threshold bandits to develop a new estimation method, which we call smoothing bandits. We demonstrate our method on a vision-based aircraft collision avoidance problem and show improvements in terms of both accuracy and efficiency over the Gaussian process and threshold bandit baselines.

One of the bottlenecks of training autonomous vehicle (AV) agents is the variability of training environments. Since learning optimal policies for unseen environments is often very costly and requires substantial data collection, it becomes computationally intractable to train the agent on every possible environment or task the AV may encounter. This paper introduces a zero-shot filtering approach to interpolate learned policies of past experiences to generalize to unseen ones. We use an experience kernel to correlate environments. These correlations are then exploited to produce policies for new tasks or environments from learned policies. We demonstrate our methods on an autonomous vehicle driving through T-intersections with different characteristics, where its behavior is modeled as a partially observable Markov decision process (POMDP). We first construct compact representations of learned policies for POMDPs with unknown transition functions given a dataset of sequential actions and observations. Then, we filter parameterized policies of previously visited environments to generate policies to new, unseen environments. We demonstrate our approaches on both an actual AV and a high-fidelity simulator. Results indicate that our experience filter offers a fast, low-effort, and near-optimal solution to create policies for tasks or environments never seen before. Furthermore, the generated new policies outperform the policy learned using the entire data collected from past environments, suggesting that the correlation among different environments can be exploited and irrelevant ones can be filtered out.

As neural networks (NNs) become more prevalent in safety-critical applications such as control of vehicles, there is a growing need to certify that systems with NN components are safe. This paper presents a set of backward reachability approaches for safety certification of neural feedback loops (NFLs), i.e., closed-loop systems with NN control policies. While backward reachability strategies have been developed for systems without NN components, the nonlinearities in NN activation functions and general noninvertibility of NN weight matrices make backward reachability for NFLs a challenging problem. To avoid the difficulties associated with propagating sets backward through NNs, we introduce a framework that leverages standard forward NN analysis tools to efficiently find over-approximations to backprojection (BP) sets, i.e., sets of states for which an NN policy will lead a system to a given target set. We present frameworks for calculating BP over-approximations for both linear and nonlinear systems with control policies represented by feedforward NNs and propose computationally efficient strategies. We use numerical results from a variety of models to showcase the proposed algorithms, including a demonstration of safety certification for a 6D system.

Due to changes in model dynamics or unexpected disturbances, an autonomous robotic system may experience unforeseen challenges during real-world operations which may affect its safety and intended behavior: in particular actuator and system failures and external disturbances are among the most common causes of degraded mode of operation. To deal with this problem, in this work, we present a meta-learning-based approach to improve the trajectory tracking performance of an unmanned aerial vehicle (UAV) under actuator faults and disturbances which have not been previously experienced. Our approach leverages meta-learning to train a model that is easily adaptable at runtime to make accurate predictions about the system's future state. A runtime monitoring and validation technique is proposed to decide when the system needs to adapt its model by considering a data pruning procedure for efficient learning. Finally, the reference trajectory is adapted based on future predictions by borrowing feedback control logic to make the system track the original and desired path without needing to access the system's controller. The proposed framework is applied and validated in both simulations and experiments on a faulty UAV navigation case study demonstrating a drastic increase in tracking performance.