Search Results for author:
Found 165 papers, 78 papers with code
Managing Geological Uncertainty in Critical Mineral Supply Chains: A POMDP Approach with Application to U.S. Lithium Resources
The world is entering an unprecedented period of critical mineral demand, driven by the global transition to renewable energy technologies and electric vehicles.
A General Bayesian Framework for Informative Input Design in System Identification
We tackle the problem of informative input design for system identification, where we select inputs, observe the corresponding outputs from the true system, and optimize the parameters of our model to best fit the data.
Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows
The latent space can be more easily explored during the search for a proposal distribution, and samples from the proposal distribution are recovered in the space of the target distribution via the invertible mapping.
Physics-informed Gaussian Processes for Safe Envelope Expansion
Flight test analysis often requires predefined test points with arbitrarily tight tolerances, leading to extensive and resource-intensive experimental campaigns.
Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement Filtering
We introduce Gradient Agreement Filtering (GAF) to improve on gradient averaging in distributed deep learning optimization.
Discrete-Time Distribution Steering using Monte Carlo Tree Search
Optimal control problems with state distribution constraints have attracted interest for their expressivity, but solutions rely on linear approximations.
More than Marketing? On the Information Value of AI Benchmarks for Practitioners
Based on the analyses of interviews with 19 individuals who have used, or decided against using, benchmarks in their day-to-day work, we find that across these settings, participants use benchmarks as a signal of relative performance difference between models.
Failure Probability Estimation for Black-Box Autonomous Systems using State-Dependent Importance Sampling Proposals
Estimating the probability of failure is a critical step in developing safety-critical autonomous systems.
BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices
We further find that most benchmarks do not report statistical significance of their results nor allow for their results to be easily replicated.
Multi-scale Generative Modeling for Fast Sampling
While working within the spatial domain can pose problems associated with ill-conditioned scores caused by power-law decay, recent advances in diffusion-based generative models have shown that transitioning to the wavelet domain offers a promising alternative.
Optimal Control of Mechanical Ventilators with Learned Respiratory Dynamics
We implement and compare controllers based on clinical guidelines contained in the ARDSnet protocol, optimal control theory, and learned latent dynamics represented as neural networks.
Semi-Markovian Planning to Coordinate Aerial and Maritime Medical Evacuation Platforms
In partnership with the United States Army, we deploy for the first time the watercraft exchange point by executing a mock patient transfer with a manikin between two HH-60M medical evacuation helicopters and an underway Army Logistic Support Vessel south of the Hawaiian island of Oahu.
Optimal Ground Station Selection for Low-Earth Orbiting Satellites
This paper presents a solution to the problem of optimal ground station selection for low-Earth orbiting (LEO) space missions that enables mission operators to precisely design their ground segment performance and costs.
Informative Input Design for Dynamic Mode Decomposition
Efficiently estimating system dynamics from data is essential for minimizing data collection costs and improving model performance.
Optimizing Falsification for Learning-Based Control Systems: A Multi-Fidelity Bayesian Approach
Using full-fidelity simulator data in this optimization problem can be computationally expensive.
Watercraft as Overwater Ambulance Exchange Points to Enhance Aeromedical Evacuation
We propose a new capability for maritime medical evacuation, which involves co-opting underway watercraft as overwater ambulance exchange points to transfer patients between medical evacuation aircraft.
Self-supervised Multi-future Occupancy Forecasting for Autonomous Driving
Environment prediction frameworks are critical for the safe navigation of autonomous vehicles (AVs) in dynamic settings.
Probabilistic Parameter Estimators and Calibration Metrics for Pose Estimation from Image Features
We present three probabilistic parameter estimators: a least-squares sampling approach, a linear approximation method, and a probabilistic programming estimator.
ASTPrompter: Weakly Supervised Automated Language Model Red-Teaming to Identify Low-Perplexity Toxic Prompts
In response, we propose a reinforcement learning formulation of LLM red-teaming designed to discover prompts that both (1) elicit toxic outputs from a defender and (2) have low perplexity as scored by that defender.
Diffusion-Based Failure Sampling for Cyber-Physical Systems
Validating safety-critical autonomous systems in high-dimensional domains such as robotics presents a significant challenge.
ConstrainedZero: Chance-Constrained POMDP Planning using Learned Probabilistic Failure Surrogates and Adaptive Safety Constraints
To plan safely in uncertain environments, agents must balance utility with safety constraints.
Addressing Myopic Constrained POMDP Planning with Recursive Dual Ascent
Lagrangian-guided Monte Carlo tree search with global dual ascent has been applied to solve large constrained partially observable Markov decision processes (CPOMDPs) online.
Entropy-regularized Point-based Value Iteration
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.
Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers
Many machine learning applications require operating on a spatially distributed dataset.
Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation
In this paper, we propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures, and we demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation.
The Synergy Between Optimal Transport Theory and Multi-Agent Reinforcement Learning
This paper explores the integration of optimal transport (OT) theory with multi-agent reinforcement learning (MARL).
Graph Q-Learning for Combinatorial Optimization
Graph-structured data is ubiquitous throughout natural and social sciences, and Graph Neural Networks (GNNs) have recently been shown to be effective at solving prediction and inference problems on graph data.
Disentangled Neural Relational Inference for Interpretable Motion Prediction
The results show superior performance compared to existing methods in modeling spatio-temporal relations, motion prediction, and identifying time-invariant latent features.
Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation
Moreover, we propose an interactivity estimation mechanism based on the difference between predicted trajectories in these two situations, which indicates the degree of influence of the ego agent on other agents.
Large-Scale Multi-Robot Assembly Planning for Autonomous Manufacturing
Mobile autonomous robots have the potential to revolutionize manufacturing processes.
Constrained Hierarchical Monte Carlo Belief-State Planning
Optimal plans in Constrained Partially Observable Markov Decision Processes (CPOMDPs) maximize reward objectives while satisfying hard cost constraints, generalizing safe planning under state and transition uncertainty.
Scene Informer: Anchor-based Occlusion Inference and Trajectory Prediction in Partially Observable Environments
We introduce the Scene Informer, a unified approach for predicting both observed agent trajectories and inferring occlusions in a partially observable setting.
SAVME: Efficient Safety Validation for Autonomous Systems Using Meta-Learning
The validation can be accelerated by identifying critical failure scenarios for the system under test and by reducing the simulation runtime.
A Holistic Assessment of the Reliability of Machine Learning Systems
As machine learning (ML) systems increasingly permeate high-stakes settings such as healthcare, transportation, military, and national security, concerns regarding their reliability have emerged.
Robust Driving Policy Learning with Guided Meta Reinforcement Learning
Although deep reinforcement learning (DRL) has shown promising results for autonomous navigation in interactive traffic scenarios, existing work typically adopts a fixed behavior policy to control social vehicles in the training environment.
Efficient Determination of Safety Requirements for Perception Systems
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.
AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator
We also provide an interface that evaluates trained models on slices of this dataset to identify changes in performance with respect to changing environmental conditions.
BetaZero: Belief-State Planning for Long-Horizon POMDPs using Learned Approximations
BetaZero learns offline approximations that replace heuristics to enable online decision making in long-horizon problems.
Model-based Validation as Probabilistic Inference
Estimating the distribution over failures is a key step in validating autonomous systems.
Joint Falsification and Fidelity Settings Optimization for Validation of Safety-Critical Systems: A Theoretical Analysis
We propose a joint falsification and fidelity optimization framework for safety validation of autonomous systems.
Bayesian Safety Validation for Failure Probability Estimation of Black-Box Systems
Estimating the probability of failure is an important step in the certification of safety-critical systems.
Optimizing Carbon Storage Operations for Long-Term Safety
In this study, we address these issues by modeling the decision-making process for carbon storage operations as a partially observable Markov decision process (POMDP).
Inferring Traffic Models in Terminal Airspace from Flight Tracks and Procedures
For each segment, a Gaussian mixture model is used to learn the deviations of aircraft trajectories from their procedures.
Falsification of Learning-Based Controllers through Multi-Fidelity Bayesian Optimization
Simulation-based falsification is a practical testing method to increase confidence that the system will meet safety requirements.
Online Planning for Constrained POMDPs with Continuous Spaces through Dual Ascent
Rather than augmenting rewards with penalties for undesired behavior, Constrained Partially Observable Markov Decision Processes (CPOMDPs) plan safely by imposing inviolable hard constraint value budgets.
A Deep Reinforcement Learning Approach to Rare Event Estimation
An important step in the design of autonomous systems is to evaluate the probability that a failure will occur.
Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction
We propose the use of evidential deep learning to estimate the epistemic uncertainty over a low-dimensional, interpretable latent space in a trajectory prediction setting.
Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning
Sparse and delayed rewards pose a challenge to single agent reinforcement learning.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
A POMDP Model for Safe Geological Carbon Sequestration
This POMDP model can be used as a test bed to drive the development of novel decision-making algorithms for CCS operations.
Optimality Guarantees for Particle Belief Approximation of POMDPs
Thus, when combined with sparse sampling MDP algorithms, this approach can yield algorithms for POMDPs that have no direct theoretical dependence on the size of the state and observation spaces.
LOPR: Latent Occupancy PRediction using Generative Models
Environment prediction frameworks are integral for autonomous vehicles, enabling safe navigation in dynamic environments.
Prioritizing emergency evacuations under compounding levels of uncertainty
However, decision makers struggle to determine optimal evacuation policies given the chaos, uncertainty, and value judgments inherent in emergency evacuations.
Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems
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.
Collaborative Decision Making Using Action Suggestions
The assumption of a collaborative environment enables us to use the agent's policy to estimate the distribution over action suggestions.
Dynamics-Aware Spatiotemporal Occupancy Prediction in Urban 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.
Sequential Bayesian Optimization for Adaptive Informative Path Planning with Multimodal Sensing
Adaptive Informative Path Planning with Multimodal Sensing (AIPPMS) considers the problem of an agent equipped with multiple sensors, each with different sensing accuracy and energy costs.
Multi-Objective Policy Gradients with Topological Constraints
Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety.
Risk-aware Meta-level Decision Making for Exploration Under Uncertainty
Robotic exploration of unknown environments is fundamentally a problem of decision making under uncertainty where the robot must account for uncertainty in sensor measurements, localization, action execution, as well as many other factors.
EvolveHypergraph: Group-Aware Dynamic Relational Reasoning for Trajectory Prediction
While the modeling of pair-wise relations has been widely studied in multi-agent interacting systems, its ability to capture higher-level and larger-scale group-wise activities is limited.
Meta-SysId: A Meta-Learning Approach for Simultaneous Identification and Prediction
In this paper, we propose Meta-SysId, a meta-learning approach to model sets of systems that have behavior governed by common but unknown laws and that differentiate themselves by their context.
Risk-Driven Design of Perception Systems
We formulate a risk function to quantify the effect of a given perceptual error on overall safety, and show how we can use it to design safer perception systems by including a risk-dependent term in the loss function and generating training data in risk-sensitive regions.
Model Predictive Optimized Path Integral Strategies
We generalize the derivation of model predictive path integral control (MPPI) to allow for a single joint distribution across controls in the control sequence.
How Do We Fail? Stress Testing Perception in Autonomous Vehicles
This paper presents a method for characterizing failures of LiDAR-based perception systems for AVs in adverse weather conditions.
Deep Binary Reinforcement Learning for Scalable Verification
We present an RL algorithm tailored specifically for BNNs.
A Mixed Integer Programming Approach for Verifying Properties of Binarized Neural Networks
We compare the runtime of our approach against state-of-the-art verification algorithms for full-precision neural networks.
Recursive Reasoning Graph for Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning (MARL) provides an efficient way for simultaneously learning policies for multiple agents interacting with each other.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Verifying Inverse Model Neural Networks
When the forward model that produced the observations is nonlinear and stochastic, solving the inverse problem is very challenging.
Conditional Approximate Normalizing Flows for Joint Multi-Step Probabilistic Forecasting with Application to Electricity Demand
In this paper, we introduce the conditional approximate normalizing flow (CANF) to make probabilistic multi-step time-series forecasts when correlations are present over long time horizons.
Dyadic Sex Composition and Task Classification Using fNIRS Hyperscanning Data
Hyperscanning with functional near-infrared spectroscopy (fNIRS) is an emerging neuroimaging application that measures the nuanced neural signatures underlying social interactions.
Autonomous Attack Mitigation for Industrial Control Systems
The proposed deep reinforcement learning approach outperforms a fully automated playbook method in simulation, taking less disruptive actions while also defending more nodes on the network.
Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models
We evaluate our method on a variety of generative models, including variational autoencoders and auto-regressive architectures.
Interpretable Local Tree Surrogate Policies
In this work, we propose a method to build predictable policy trees as surrogates for policies such as neural networks.
Multi-Agent Variational Occlusion Inference Using People as Sensors
We propose an occlusion inference method that characterizes observed behaviors of human agents as sensor measurements, and fuses them with those from a standard sensor suite.
OVERT: An Algorithm for Safety Verification of Neural Network Control Policies for Nonlinear Systems
In response to this challenge, we present OVERT: a sound algorithm for safety verification of nonlinear discrete-time closed loop dynamical systems with neural network control policies.
Finding Failures in High-Fidelity Simulation using Adaptive Stress Testing and the Backward Algorithm
Validating the safety of autonomous systems generally requires the use of high-fidelity simulators that adequately capture the variability of real-world scenarios.
3D Radar Velocity Maps for Uncertain Dynamic Environments
This paper explores a Bayesian approach that captures our uncertainty in the map given training data.
Reinforcement Learning for Industrial Control Network Cyber Security Orchestration
Defending computer networks from cyber attack requires coordinating actions across multiple nodes based on imperfect indicators of compromise while minimizing disruptions to network operations.
ZoPE: A Fast Optimizer for ReLU Networks with Low-Dimensional Inputs
We demonstrate how to formulate and solve three types of optimization problems: (i) minimization of any convex function over the output space, (ii) minimization of a convex function over the output of two networks in series with an adversarial perturbation in the layer between them, and (iii) maximization of the difference in output between two networks.
Measurable Monte Carlo Search Error Bounds
Monte Carlo planners can often return sub-optimal actions, even if they are guaranteed to converge in the limit of infinite samples.
Verification of Image-based Neural Network Controllers Using Generative Models
For this reason, recent work has focused on combining techniques in formal methods and reachability analysis to obtain guarantees on the closed-loop performance of neural network controllers.
Training Structured Mechanical Models by Minimizing Discrete Euler-Lagrange Residual
Structured Mechanical Models (SMMs) are a data-efficient black-box parameterization of mechanical systems, typically fit to data by minimizing the error between predicted and observed accelerations or next states.
Generating Probabilistic Safety Guarantees for Neural Network Controllers
In this work, we develop a method to use the results from neural network verification tools to provide probabilistic safety guarantees on a neural network controller.
Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning
Communication is a important factor that enables agents work cooperatively in multi-agent reinforcement learning (MARL).
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Scalable Anytime Planning for Multi-Agent MDPs
We also introduce a multi-drone delivery domain with dynamic, i. e., state-dependent coordination graphs, and demonstrate how our approach scales to large problems on this domain that are intractable for other MCTS methods.
Transfer Learning for Efficient Iterative Safety Validation
Safety validation is important during the development of safety-critical autonomous systems but can require significant computational effort.
Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships
Deep reinforcement learning (DRL) provides a promising way for learning navigation in complex autonomous driving scenarios.
Adaptive Stress Testing of Trajectory Predictions in Flight Management Systems
To find failure events and their likelihoods in flight-critical systems, we investigate the use of an advanced black-box stress testing approach called adaptive stress testing.
Out-of-Distribution Detection for Automotive Perception
A mechanism to detect OOD samples is important for safety-critical applications, such as automotive perception, to trigger a safe fallback mode.
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.
Attention Augmented ConvLSTM for Environment Prediction
Safe and proactive planning in robotic systems generally requires accurate predictions of the environment.
Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders
Discrete latent spaces in variational autoencoders have been shown to effectively capture the data distribution for many real-world problems such as natural language understanding, human intent prediction, and visual scene representation.
Bayesian Optimized Monte Carlo Planning
Monte Carlo tree search with progressive widening attempts to improve scaling by sampling from the action space to construct a policy search tree.
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.
Global Optimization of Objective Functions Represented by ReLU Networks
However, individual "yes or no" questions cannot answer qualitative questions such as "what is the largest error within these bounds"; the answers to these lie in the domain of optimization.
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.
A Maximum Independent Set Method for Scheduling Earth Observing Satellite Constellations
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.
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.
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.
Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
Coordination graph based formalization allows reasoning about the joint action based on the structure of interactions.
Towards Recurrent Autoregressive Flow Models
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.
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).
A Taxonomy and Review of Algorithms for Modeling and Predicting Human Driver Behavior
We present a review and taxonomy of 200 models from the literature on driver behavior modeling.
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.
Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic
This approach exposes the agent to a broad variety of behaviors during training, which promotes learning policies that are robust to model discrepancies.
A Survey of Algorithms for Black-Box Safety Validation of Cyber-Physical Systems
Autonomous cyber-physical systems (CPS) can improve safety and efficiency for safety-critical applications, but require rigorous testing before deployment.
Active Preference-Based Gaussian Process Regression for Reward Learning
Our results in simulations and a user study suggest that our approach can efficiently learn expressive reward functions for robotics tasks.
Structured Mechanical Models for Robot Learning and Control
Deep neural networks have been used to learn models of robot dynamics from data, but they suffer from data-inefficiency and the difficulty to incorporate prior knowledge.
Scalable Autonomous Vehicle Safety Validation through Dynamic Programming and Scene Decomposition
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.
Interpretable Safety Validation for Autonomous Vehicles
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.
The Adaptive Stress Testing Formulation
Validation is a key challenge in the search for safe autonomy.
Adaptive Stress Testing without Domain Heuristics using Go-Explore
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.
Adaptive Informative Path Planning with Multimodal Sensing
AIPPMS requires reasoning jointly about the effects of sensing and movement in terms of both energy expended and information gained.
Exchangeable Input Representations for Reinforcement Learning
We show that our proposed representation results in an input space that is a factor of $m!$ smaller for inputs of $m$ objects.
Point-Based Methods for Model Checking in Partially Observable Markov Decision Processes
Autonomous systems are often required to operate in partially observable environments.
Monte-Carlo Tree Search for Policy Optimization
Gradient-based methods are often used for policy optimization in deep reinforcement learning, despite being vulnerable to local optima and saddle points.
Guaranteeing Safety for Neural Network-Based Aircraft Collision Avoidance Systems
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.
Parameter-Conditioned Sequential Generative Modeling of Fluid Flows
The computational cost associated with simulating fluid flows can make it infeasible to run many simulations across multiple flow conditions.
Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model
This paper focuses on the problem of computing an $\epsilon$-optimal policy in a discounted Markov Decision Process (MDP) provided that we can access the reward and transition function through a generative model.
Limiting Extrapolation in Linear Approximate Value Iteration
We prove that if the features at any state can be represented as a convex combination of features at the anchor points, then errors are propagated linearly over iterations (instead of exponentially) and our method achieves a polynomial sample complexity bound in the horizon and the number of anchor points.
Efficient Large-Scale Multi-Drone Delivery Using Transit Networks
Our results show that the framework computes solutions typically within a few seconds on commodity hardware, and that drones travel up to $360 \%$ of their flight range with public transit.
Non-linear System Identification from Partial Observations via Iterative Smoothing and Learning
System identification is the process of building a mathematical model of an unknown system from measurements of its inputs and outputs.
Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation
Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems.
Health-Informed Policy Gradients for Multi-Agent Reinforcement Learning
This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function.
Multi-agent Reinforcement Learning
Policy Gradient Methods
+3
Learning an Urban Air Mobility Encounter Model from Expert Preferences
Airspace models have played an important role in the development and evaluation of aircraft collision avoidance systems for both manned and unmanned aircraft.
Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic
In this work, we present a reinforcement learning approach to learn how to interact with drivers with different cooperation levels.
Hybrid Planning for Dynamic Multimodal Stochastic Shortest Paths
Sequential decision problems in applications such as manipulation in warehouses, multi-step meal preparation, and routing in autonomous vehicle networks often involve reasoning about uncertainty, planning over discrete modes as well as continuous states, and reacting to dynamic updates.
Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving
This paper introduces a general framework for tactical decision making, which combines the concepts of planning and learning, in the form of Monte Carlo tree search and deep reinforcement learning.
Dynamic Environment Prediction in Urban Scenes using Recurrent Representation Learning
A key challenge for autonomous driving is safe trajectory planning in cluttered, urban environments with dynamic obstacles, such as pedestrians, bicyclists, and other vehicles.
Pedestrian Collision Avoidance System for Scenarios with Occlusions
We show that combining the two approaches provides a robust autonomous braking system that reduces unnecessary braking caused by using the AEB system on its own.
Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments
Navigating urban environments represents a complex task for automated vehicles.
Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving
We propose a generic approach to enforce probabilistic guarantees on an RL agent.
Algorithms for Verifying Deep Neural Networks
Deep neural networks are widely used for nonlinear function approximation with applications ranging from computer vision to control.
Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning
Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers.
Rethinking System Health Management
Health management of complex dynamic systems has traditionally evolved separately from automated control, planning, and scheduling (generally referred to in the paper as decision making).
Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learning
To improve efficiency and reduce failures in autonomous vehicles, research has focused on developing robust and safe learning methods that take into account disturbances in the environment.
Model Primitive Hierarchical Lifelong Reinforcement Learning
Learning interpretable and transferable subpolicies and performing task decomposition from a single, complex task is difficult.
Deep Variational Koopman Models: Inferring Koopman Observations for Uncertainty-Aware Dynamics Modeling and Control
We introduce the Deep Variational Koopman (DVK) model, a method for inferring distributions over observations that can be propagated linearly in time.
A General Framework for Structured Learning of Mechanical Systems
We address the need for a flexible, gray-box model of mechanical systems that can seamlessly incorporate prior knowledge where it is available, and train expressive function approximators where it is not.
Model-based Reinforcement Learning
Reinforcement Learning
+1
Adaptive Stress Testing for Autonomous Vehicles
This paper presents Monte Carlo Tree Search (MCTS) and Deep Reinforcement Learning (DRL) solutions that can scale to large environments.
Dynamic Real-time Multimodal Routing with Hierarchical Hybrid Planning
We introduce the problem of Dynamic Real-time Multimodal Routing (DREAMR), which requires planning and executing routes under uncertainty for an autonomous agent.
Real-time Prediction of Automotive Collision Risk from Monocular Video
Many automotive applications, such as Advanced Driver Assistance Systems (ADAS) for collision avoidance and warnings, require estimating the future automotive risk of a driving scene.
Visual Depth Mapping from Monocular Images using Recurrent Convolutional Neural Networks
A reliable sense-and-avoid system is critical to enabling safe autonomous operation of unmanned aircraft.
Robust Super-Level Set Estimation using Gaussian Processes
This paper focuses on the problem of determining as large a region as possible where a function exceeds a given threshold with high probability.
Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning
Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems and autonomous cars.
Deep Neural Network Compression for Aircraft Collision Avoidance Systems
One approach to designing decision making logic for an aircraft collision avoidance system frames the problem as a Markov decision process and optimizes the system using dynamic programming.
Distributed Wildfire Surveillance with Autonomous Aircraft using Deep Reinforcement Learning
Teams of autonomous unmanned aircraft can be used to monitor wildfires, enabling firefighters to make informed decisions.
Image-based Guidance of Autonomous Aircraft for Wildfire Surveillance and Prediction
The second approach uses a particle filter to predict wildfire growth and uses observations to estimate uncertainties relating to wildfire expansion.
Using Neural Networks to Generate Information Maps for Mobile Sensors
A common method uses information maps that estimate the value of taking measurements from any point in the sensor state space.
EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning
While imitation learning is often used in robotics, the approach frequently suffers from data mismatch and compounding errors.
Amortized Inference Regularization
In this paper, we leverage the fact that VAEs rely on amortized inference and propose techniques for amortized inference regularization (AIR) that control the smoothness of the inference model.
Deep Dynamical Modeling and Control of Unsteady Fluid Flows
The design of flow control systems remains a challenge due to the nonlinear nature of the equations that govern fluid flow.
Multi-Agent Imitation Learning for Driving Simulation
Simulation is an appealing option for validating the safety of autonomous vehicles.
Decomposition Methods with Deep Corrections for Reinforcement Learning
In contexts where an agent interacts with multiple entities, utility decomposition can be used to separate the global objective into local tasks considering each individual entity independently.
Real-time Prediction of Intermediate-Horizon Automotive Collision Risk
Advanced collision avoidance and driver hand-off systems can benefit from the ability to accurately predict, in real time, the probability a vehicle will be involved in a collision within an intermediate horizon of 10 to 20 seconds.
Burn-In Demonstrations for Multi-Modal Imitation Learning
Recent work on imitation learning has generated policies that reproduce expert behavior from multi-modal data.
Deep Reinforcement Learning for Event-Driven Multi-Agent Decision Processes
The incorporation of macro-actions (temporally extended actions) into multi-agent decision problems has the potential to address the curse of dimensionality associated with such decision problems.
DropoutDAgger: A Bayesian Approach to Safe Imitation Learning
While imitation learning is becoming common practice in robotics, this approach often suffers from data mismatch and compounding errors.
Towards Proving the Adversarial Robustness of Deep Neural Networks
Autonomous vehicles are highly complex systems, required to function reliably in a wide variety of situations.
Interpretable Categorization of Heterogeneous Time Series Data
In particular, when a grammar based on temporal logic is used, we show that GBDTs can be used for the interpretable classi cation of high-dimensional and heterogeneous time series data.
Closed-Loop Policies for Operational Tests of Safety-Critical Systems
Manufacturers of safety-critical systems must make the case that their product is sufficiently safe for public deployment.
Simultaneous Policy Learning and Latent State Inference for Imitating Driver Behavior
In this work, we propose a method for learning driver models that account for variables that cannot be observed directly.
Belief State Planning for Autonomously Navigating Urban Intersections
Urban intersections represent a complex environment for autonomous vehicles with many sources of uncertainty.
Robotics
Exploiting Anonymity in Approximate Linear Programming: Scaling to Large Multiagent MDPs (Extended Version)
We present an approach to mitigate this limitation for certain types of multiagent systems, exploiting a property that can be thought of as "anonymous influence" in the factored MDP.
Predicting the behavior of interacting humans by fusing data from multiple sources
Multi-fidelity methods combine inexpensive low-fidelity simulations with costly but highfidelity simulations to produce an accurate model of a system of interest at minimal cost.
A Comparison of Monte Carlo Tree Search and Mathematical Optimization for Large Scale Dynamic Resource Allocation
In this paper, we adapt both MCTS and MO to a problem inspired by tactical wildfire and management and undertake an extensive computational study comparing the two methods on large scale instances in terms of both the state and the action spaces.
