Andrew Best

University of North Carolina at Chapel Hill | UNC · Department of Computer Science

We present a novel approach for generating plausible verbal interactions between virtual human-like agents and user avatars in shared virtual environments. Sense-Plan-Ask, or SPA, extends prior work in propositional planning and natural language processing to enable agents to plan with uncertain information, and leverage question and answer dialogu...

We consider the problem of using reinforcement learning to train adversarial agents for automatic testing and falsification of cyberphysical systems, such as autonomous vehicles, robots, and airplanes. In order to produce useful agents, however, it is useful to be able to control the degree of adversariality by specifying rules that an agent must f...

We present a real-time algorithm to infer the intention of a user's avatar in a virtual environment shared with multiple human-like agents. Our algorithm applies the Bayesian Theory of Mind approach to make inferences about the avatar's hidden intentions based on the observed proxemics and gaze-based cues. Our approach accounts for the potential ir...

This study investigated how humans interact socially with robots. Participants engaged in a hallway navigation task with a robot. Throughout twelve trials, the display on the robot and its proxemics behavior was varied while participants were tasked with first, reacting to the robot’s actions and second, interpreting its behavior. Results indicated...

Increased vehicle safety is a driving force in the development of Connected Vehicle (CV) and Automated Vehicle (AV) technologies. Unlike traditional in-vehicle safety features, CV and AV technologies help avoid catastrophes all together with advanced warnings of impending danger and beyond human reaction times. Although extensive efforts are underw...

We present an interactive algorithm to generate plausible movements for human-like agents interacting with other agents or avatars in a virtual environment. Our approach takes into account high-dimensional human motion constraints and bio-mechanical constraints to compute collision-free trajectories for each agent. We conducted a study to investiga...

We present a novel algorithm for generating virtual avatars which move like the represented human subject, using inexpensive sensors & commodity hardware. Our algorithm is based on a perceptual study that evaluates self-recognition and similarity of gaits rendered on virtual avatars. We identify discriminatory features of human gait and propose a d...

This paper describes initial validation of a theoretical framework to support research on the visualization of uncertainty. Two experiments replicated and extended this framework, illustrating how the manipulation of task complexity produces differences in performance. Additionally, using a combinatory metric of workload and performance, this frame...

Current 3D capture and modeling technology can rapidly generate highly photo-realistic 3D avatars of human subjects. However, while the avatars look like their human counterparts, their movements often do not mimic their own due to existing challenges in accurate motion capture and re-targeting. A better understanding of factors that influence the...

We present AutonoVi:, a novel algorithm for autonomous vehicle navigation that supports dynamic maneuvers and satisfies traffic constraints and norms. Our approach is based on optimization-based maneuver planning that supports dynamic lane-changes, swerving, and braking in all traffic scenarios and guides the vehicle to its goal position. We take i...

We present a practical approach for interactive crowd simulation based on elliptical agents. Our formulation uses a biomechanically accurate pedestrian representation to simulate different local interactions, including backpedaling, side-stepping, and shoulder-twisting. We present an efficient algorithm for local navigation and collision avoidance...

We present a novel interactive approach, PedVR, to generate plausible behaviors for a large number of virtual humans, and to enable natural interaction between the real user and virtual agents. Our formulation is based on a coupled approach that combines a 2D multi-agent navigation algorithm with 3D human motion synthesis. The coupling can result i...

Using research in social cognition as a foundation, the present study examined the degree to which mental state attributions are influenced by rapid versus reflective judgment. We observed differences in response times and did not find significant differences in the accuracy of mental state attributions. Results indicated that participants perceive...

*HFES 2016 Cognitive Engineering Technical Group Best Student Paper - 3rd place* Robotic teammates are becoming prevalent in increasingly complex and dynamic operational and social settings. For this reason, the perception of robots operating in such environments has transitioned from the perception of robots as tools, extending human capabilities...

Robotic teammates are becoming prevalent in increasingly complex and dynamic operational and social settings. For this reason, the perception of robots operating in such environments has transitioned from the perception of robots as tools, extending human capabilities, to the perception of robots as teammates, collaborating with humans and displayi...

We present a novel algorithm for real-time collision-free navigation between elliptical agents. Each robot or agent is represented using a tight-fitting 2D ellipse in the plane. We extend the reciprocal velocity obstacle formulation by using conservative linear approximations of ellipses and derive sufficient conditions for collision-free motion ba...

Human-robot teaming largely relies on the ability of machines to respond and relate to human social signals. Prior work in Social Signal Processing has drawn a distinction between social cues (discrete, observable features) and social signals (underlying meaning). For machines to attribute meaning to behavior, they must first understand some probab...

We present Menge, a cross-platform, extensible, modular framework for simulating pedestrian movement in a crowd. Menge's architecture is inspired by an implicit decomposition of the problem of simulating crowds into component subproblems. These subproblems can typically be solved in many ways; different combinations of subproblem solutions yield cr...

We present a multi-agent simulation algorithm to compute the trajectories and full-body motion of human-like agents. Our formulation uses a coupled approach that combines 2D collision-free navigation with high-DOF human motion simulation using a behavioral finite state machine. In order to generate plausible pedestrian motion, we use a closed-loop...

Pedestrian crowds often have been modeled as many-particle system including microscopic multi-agent simulators. One of the key challenges is to unearth governing principles that can model pedestrian movement, and use them to reproduce paths and behaviors that are frequently observed in human crowds. To that effect, we present a novel crowd simulati...

We present Ped-Air, a pedestrian simulation system to model the loading, unloading, and evacuation of commercial aircraft. We address the challenge of simulating passenger movement in constrained spaces (e.g., aisles and rows), along with complex, coordinating behaviors between the passengers. Ped-Air models different categories of passengers and f...

We present a novel algorithm to model density-dependent behaviors in crowd simulation. Our approach aims to generate pedestrian trajectories that correspond to the speed/density relationships that are typically expressed using the Fundamental Diagram. The algorithm's formulation can be easily combined with well-known multi-agent simulation techniqu...