Safety-critical systems often operate in partially observable environments, where assessing the safety of the underlying policy remains a fundamental challenge. This study focuses on evaluating policies by identifying regions of the belief-space that can lead the system’s policy to an undesirable state with a non-negligible probability. In this paper, we introduce Backward Monte Carlo Tree Search, the first Monte Carlo tree search framework that expands backward in time within the belief-space. The tree search begins from an undesired terminal belief and recursively explores its possible predecessors, constructing a tree of belief transitions that could lead to an unsafe outcome within a given horizon. Evaluations in gridworld and autonomous driving domains show that identifying beliefs from which failures may occur enables runtime risk forecasting and targeted policy retraining, marking a conceptual shift in how safety is validated under uncertainty.

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.

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.

This paper addresses a safe planning and control problem for mobile robots operating in communication- and sensor-limited dynamic environments. In this case the robots cannot sense the objects around them and must instead rely on intermittent, external information about the environment, as e.g., in underwater applications. The challenge in this case is that the robots must plan using only this stale data, while accounting for any noise in the data or uncertainty in the environment. To address this challenge we propose a compositional technique which leverages neural networks to quickly plan and control a robot through crowded and dynamic environments using only intermittent information. Specifically, our tool uses reachability analysis and potential fields to train a neural network that is capable of generating safe control actions. We demonstrate our technique both in simulation with an underwater vehicle crossing a crowded shipping channel and with real experiments with ground vehicles in communication-and sensor-limited environments.

Detection and segmentation of moving obstacles, along with prediction of the future occupancy states of the local environment, are essential for autonomous vehicles to proactively make safe and informed decisions. In this paper, we propose a framework that integrates the two capabilities together using deep neural network architectures. Our method first detects and segments moving objects in the scene, and uses this information to predict the spatiotemporal evolution of the environment around autonomous vehicles. to address the problem of direct integration of both static-dynamic object segmentation and environment prediction models, we propose using occupancy-based environment representations across the whole framework. Our method is validated on the real-world Waymo Open Dataset and demonstrates higher prediction accuracy than baseline methods.

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.

Autonomous vehicles are typically developed and trained to work under certain system and environmental conditions defined at design time and can fail or perform poorly if unforeseen conditions such as disturbances or changes in model dynamics appear at runtime. In this work, we present a fast online planning, learning, and recovery approach for safe autonomous operations under unknown runtime disturbances. Our approach estimates the behavior of the system with an unknown model and provides safe plans at runtime under previously unseen disturbances by leveraging Gaussian Process regression theory in which a model is continuously trained and adapted using data collected during the autonomous operation. A recovery procedure is event-triggered any time a safety constraint is violated to guarantee safety and enable learning and replanning. The proposed framework is applied and validated both in simulation and experiment on an unmanned aerial vehicle (UAV) delivery case study in which the UAV is tasked to carry an a priori unknown payload to a goal location in a cluttered/constrained environment.

In this paper, we present a fast run-time monitoring framework for safety assurance during autonomous system operations in uncertain environments. Modern unmanned vehicles rely on periodic sensor measurements for motion planning and control. However, a vehicle may not always be able to obtain its state information due to various reasons such as sensor failures, signal occlusions, and communication problems. To guarantee the safety of a system during these circumstances under the presence of disturbance and noise, we propose a novel fast reachability analysis approach that leverages Gaussian process regression theory to predict future states of the system at run-time. We also propose a self/event-triggered monitoring and replanning approach which leverages our fast reachability scheme to recover the system when needed and replan its trajectory to guarantee safety constraints (i.e., the system will not collide with any obstacles). Our technique is validated both with simulations and experiments on unmanned aerial vehicles case studies in cluttered environments under the effect of unknown wind disturbance at run-time.

Modern unmanned aerial vehicles (UAVs) rely on constant periodic sensor measurements to detect and avoid obstacles. However, constant checking and replanning are time and energy consuming and are often not necessary especially in situations in which the UAV can safely fly in uncluttered environments without entering unsafe states. Thus, in this paper, we propose a self-triggered framework that leverages reachability analysis to schedule the next time to check sensor measurements and perform replanning while guaranteeing safety under noise and disturbance effects. Further, we relax sensor checking and motion replanning operations by leveraging a risk-based analysis that determines the likelihood to reach undesired states over a certain time horizon. We also propose an online speed adaptation policy based on the planned trajectory curvature to minimize drift from the desired path due to the system dynamics. Finally, we validate the proposed approach with simulations and experiments for a quadrotor UAV motion planning case study in a cluttered environment.