Jonathan DeCastro
YOU?
Author Swipe
View article: Safety with Agency: Human-Centered Safety Filter with Application to AI-Assisted Motorsports
Safety with Agency: Human-Centered Safety Filter with Application to AI-Assisted Motorsports Open
View article: Computational Teaching for Driving via Multi-Task Imitation Learning
Computational Teaching for Driving via Multi-Task Imitation Learning Open
Learning motor skills for sports or performance driving is often done with professional instruction from expert human teachers, whose availability is limited. Our goal is to enable automated teaching via a learned model that interacts with…
View article: Personalizing driver safety interfaces via driver cognitive factors inference
Personalizing driver safety interfaces via driver cognitive factors inference Open
View article: Think Deep and Fast: Learning Neural Nonlinear Opinion Dynamics from Inverse Dynamic Games for Split-Second Interactions
Think Deep and Fast: Learning Neural Nonlinear Opinion Dynamics from Inverse Dynamic Games for Split-Second Interactions Open
Non-cooperative interactions commonly occur in multi-agent scenarios such as car racing, where an ego vehicle can choose to overtake the rival, or stay behind it until a safe overtaking "corridor" opens. While an expert human can do well a…
View article: Blending Data-Driven Priors in Dynamic Games
Blending Data-Driven Priors in Dynamic Games Open
As intelligent robots like autonomous vehicles become increasingly deployed in the presence of people, the extent to which these systems should leverage model-based game-theoretic planners versus data-driven policies for safe, interaction-…
View article: Personalizing Driver Safety Interfaces via Driver Cognitive Factors Inference
Personalizing Driver Safety Interfaces via Driver Cognitive Factors Inference Open
Recent advances in AI and intelligent vehicle technology hold promise to revolutionize mobility and transportation, in the form of advanced driving assistance (ADAS) interfaces. Although it is widely recognized that certain cognitive facto…
View article: A Safe Preference Learning Approach for Personalization with Applications to Autonomous Vehicles
A Safe Preference Learning Approach for Personalization with Applications to Autonomous Vehicles Open
This work introduces a preference learning method that ensures adherence to given specifications, with an application to autonomous vehicles. Our approach incorporates the priority ordering of Signal Temporal Logic (STL) formulas describin…
View article: NashFormer: Leveraging Local Nash Equilibria for Semantically Diverse Trajectory Prediction
NashFormer: Leveraging Local Nash Equilibria for Semantically Diverse Trajectory Prediction Open
Interactions between road agents present a significant challenge in trajectory prediction, especially in cases involving multiple agents. Because existing diversity-aware predictors do not account for the interactive nature of multi-agent …
View article: Specification-Guided Data Aggregation for Semantically Aware Imitation Learning
Specification-Guided Data Aggregation for Semantically Aware Imitation Learning Open
Advancements in simulation and formal methods-guided environment sampling have enabled the rigorous evaluation of machine learning models in a number of safety-critical scenarios, such as autonomous driving. Application of these environmen…
View article: Learning Latent Traits for Simulated Cooperative Driving Tasks
Learning Latent Traits for Simulated Cooperative Driving Tasks Open
To construct effective teaming strategies between humans and AI systems in complex, risky situations requires an understanding of individual preferences and behaviors of humans. Previously this problem has been treated in case-specific or …
View article: Classification of Driving Behaviors Using STL Formulas: A Comparative Study
Classification of Driving Behaviors Using STL Formulas: A Comparative Study Open
View article: Analyzing Multiagent Interactions in Traffic Scenes via Topological Braids
Analyzing Multiagent Interactions in Traffic Scenes via Topological Braids Open
We focus on the problem of analyzing multiagent interactions in traffic domains. Understanding the space of behavior of real-world traffic may offer significant advantages for algorithmic design, data-driven methodologies, and benchmarking…
View article: The Logical Options Framework
The Logical Options Framework Open
Learning composable policies for environments with complex rules and tasks is a challenging problem. We introduce a hierarchical reinforcement learning framework called the Logical Options Framework (LOF) that learns policies that are sati…
View article: Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features
Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features Open
IEEE In this work, we propose a novel approach for integrating rules into traffic agent trajectory prediction. Consideration of rules is important for understanding how people behave --- yet, it cannot be assumed that rules are always foll…
View article: Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation
Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation Open
Automated Vehicles require exhaustive testing in simulation to detect as many safety-critical failures as possible before deployment on public roads. In this work, we focus on the core decision-making component of autonomous robots: their …
View article: Autonomous Vehicle Battery State-of-Charge Prognostics Enhanced Mission Planning
Autonomous Vehicle Battery State-of-Charge Prognostics Enhanced Mission Planning Open
Most mission planning algorithms are designed for healthy systems. When faults occur in a system, it is advantageous to optimize the mission plan by taking the system health condition into consideration. In this paper, a mission planning s…
View article: Behaviorally Diverse Traffic Simulation via Reinforcement Learning
Behaviorally Diverse Traffic Simulation via Reinforcement Learning Open
Traffic simulators are important tools in autonomous driving development. While continuous progress has been made to provide developers more options for modeling various traffic participants, tuning these models to increase their behaviora…
View article: Implicit Multi-Agent Coordination at Unsignalized Intersections via Topological Inference.
Implicit Multi-Agent Coordination at Unsignalized Intersections via Topological Inference. Open
We focus on navigation among rational, non-communicating agents at unsignalized street intersections. Following collision-free motion under such settings demands nuanced implicit coordination among agents. Often, the structure of these dom…
View article: Implicit Multiagent Coordination at Unsignalized Intersections via Multimodal Inference Enabled by Topological Braids
Implicit Multiagent Coordination at Unsignalized Intersections via Multimodal Inference Enabled by Topological Braids Open
We focus on navigation among rational, non-communicating agents at unsignalized street intersections. Following collision-free motion under such settings demands nuanced implicit coordination among agents. Often, the structure of these dom…
View article: CARPAL: Confidence-Aware Intent Recognition for Parallel Autonomy
CARPAL: Confidence-Aware Intent Recognition for Parallel Autonomy Open
Predicting driver intentions is a difficult and crucial task for advanced driver assistance systems. Traditional confidence measures on predictions often ignore the way predicted trajectories affect downstream decisions for safe driving. I…
View article: DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling
DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling Open
Vehicle trajectory prediction is crucial for autonomous driving and advanced driver assistant systems. While existing approaches may sample from a predicted distribution of vehicle trajectories, they lack the ability to explore it -- a key…
View article: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling.
Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling. Open
Vehicle trajectory prediction is crucial for autonomous driving and advanced driver assistant systems. While existing approaches may sample from a predicted distribution of vehicle trajectories, they lack the ability to explore it - a key …
View article: Better AI through Logical Scaffolding
Better AI through Logical Scaffolding Open
We describe the concept of logical scaffolds, which can be used to improve the quality of software that relies on AI components. We explain how some of the existing ideas on runtime monitors for perception systems can be seen as a specific…
View article: Reactive mission and motion planning with deadlock resolution avoiding dynamic obstacles
Reactive mission and motion planning with deadlock resolution avoiding dynamic obstacles Open
In the near future mobile robots, such as personal robots or mobile manipulators, will share the workspace with other robots and humans. We present a method for mission and motion planning that applies to small teams of robots performing a…
View article: Reactive mission and motion planning with deadlock resolution avoiding dynamic obstacles
Reactive mission and motion planning with deadlock resolution avoiding dynamic obstacles Open
View article: Guaranteeing Reactive Missions for Complex Robotic Systems
Guaranteeing Reactive Missions for Complex Robotic Systems Open
With the availability of robots capable of performing complex missions, formal approaches to controller synthesis are gaining increasing attention as a means for synthesizing controllers that guarantee, by construction, the execution of su…