Michael Novitzky

Bio-inspired multi-robot communication through behavior recognition

This paper focuses on enabling multi-robot teams to cooperatively perform tasks without the use of radio or acoustic communication. One key to more effective cooperative interaction in a multi-robot team is the ability to understand the behavior and intent of other robots. This is similar to the honey bee “waggle dance” in which a bee can communicate the orientation and distance of a food source. In this similar manner, our heterogenous multi-robot team uses a specific behavior to indicate the location of mine-like objects (MLOs). Observed teammate action sequences can be learned to perform behavior recognition and task-assignment in the absence of communication. We apply Conditional Random Fields (CRFs) to perform behavior recognition as an approach to task monitoring in the absence of communication in a challenging underwater environment. In order to demonstrate the use of behavior recognition of an Autonomous Underwater Vehicle (AUV) in a cooperative task, we use trajectory based techniques for model generation and behavior discrimination in experiments using simulated scenario data. Results are presented demonstrating heterogenous teammate cooperation between an AUV and an Autonomous Surface Vehicle (ASV) using behavior recognition rather than radio or acoustic communication in a mine clearing task.

Grocery hunter: a fun mobile game for children to combat obesity

This paper presents a handheld mobile game, Grocery Hunter that encourages children to take on healthy eating habits. Children can use a pocket PC to play the Grocery Hunter game to learn about food nutrition and healthy food choices. Childhood obesity in the United States has already reached epidemic proportions. The best way to help children attain and maintain healthy weight is through physical activity and nutritious eating. Our design addresses nutrition directly by teaching children healthy eating habits using an interactive game in the grocery store.

Duckietown: An open, inexpensive and flexible platform for autonomy education and research

Duckietown is an open, inexpensive and flexible platform for autonomy education and research. The platform comprises small autonomous vehicles (“Duckiebots”) built from off-the-shelf components, and cities (“Duckietowns”) complete with roads, signage, traffic lights, obstacles, and citizens (duckies) in need of transportation. The Duckietown platform offers a wide range of functionalities at a low cost. Duckiebots sense the world with only one monocular camera and perform all processing onboard with a Raspberry Pi 2, yet are able to: follow lanes while avoiding obstacles, pedestrians (duckies) and other Duckiebots, localize within a global map, navigate a city, and coordinate with other Duckiebots to avoid collisions. Duckietown is a useful tool since educators and researchers can save money and time by not having to develop all of the necessary supporting infrastructure and capabilities. All materials are available as open source, and the hope is that others in the community will adopt the platform for education and research.

AUV behavior recognition using behavior histograms, HMMs, and CRFs

This paper focuses on behavior recognition in an underwater application as a substitute for communicating through acoustic transmissions, which can be unreliable. The importance of this work is that sensor information regarding other agents can be leveraged to perform behavior recognition, which is activity recognition of robots performing specific programmed behaviors, and task-assignment. This work illustrates the use of Behavior Histograms, Hidden Markov Models (HMMs), and Conditional Random Fields (CRFs) to perform behavior recognition. We present challenges associated with using each behavior recognition technique along with results on individually selected test trajectories, from simulated and real sonar data, and real-time recognition through a simulated mission.

Collision avoidance road test for COLREGS-constrained autonomous vehicles

Recently developed algorithms quantify and subsequently evaluate COLREGS performance in collision avoidance scenarios based on vessel track data. Combining these evaluation algorithms with proposed categories of COLREGS rules allows for testing of collision avoidance performance in accordance with protocol requirements. This paper proposes a “road test” framework for autonomous marine vehicles prior to operating outside of a testing environment. Testing and certifying agencies may adopt the proposed categories of scope and testing attributes while determining the appropriate parameters for evaluation. Adapting the evaluation criteria to several thresholds would allow for various levels of certification and locally-tailored customs. Generalization to human operators and other domains such as Rules of the Air is proposed.

A Human-Robot Speech Interface for an Autonomous Marine Teammate

There is current interest in creating human-robot teams in which a human operator is in its own conveyance teaming up with several autonomous teammates. In this work we focus on human-robot teamwork in the marine environment as it is challenging and can serve as a surrogate for other environments. Marine elements such as wind speed, air temperature, water, obstacles, and ambient noise can have drastic implications for team performance. Our goal is to create a human-robot system that can join many humans and many robots together to cooperatively perform tasks in such challenging environments. In this paper, we present our human-robot speech dialog system and compare participant responses to having human versus autonomous vehicle teammates escorting and holding station at locations of interest.

Conditional Random Fields for Behavior Recognition of Autonomous Underwater Vehicles

This paper focuses on multi-robot teams working cooperatively in an underwater application. Multi-robot teams working cooperatively to perform multiple tasks simultaneously have the potential to be more robust to failure and efficient when compared to single robot solutions. One key to more effective interaction is the ability to identify the behavior of other agents. However, the underwater environment presents specific challenges to teammate behavior identification. Current decentralized collaboration approaches, such as auction-based methods, degrade in poor communication environments. Sensor information regarding teammates can be leveraged to perform behavior recognition and task-assignment in the absence of communication. This work illustrates the use of Conditional Random Fields (CRFs) to perform behavior recognition as an approach to task monitoring in the absence of robust communication in a challenging underwater environment. In order to demonstrate the feasibility of performing behavior recognition of an AUV in the underwater domain, we use trajectory based techniques for model generation and behavior discrimination in experiments using simulated trajectories and real sonar data. Results are presented with comparison of a CRF method to one using Hidden Markov Models.

Preliminary Interactions of Human-Robot Trust, Cognitive Load, and Robot Intelligence Levels in a Competitive Game

This paper presents a pilot study in which we examine the interactions between human-robot teammate trust, cognitive load, and robot intelligence levels. In particular, we attempt to assess these interactions during a competitive game of capture the flag played between a human and a robot. We present results while the human plays against robots of different intelligence levels and determines their level of trust of each robot as a potential teammate through a post experiment questionnaire. We also present our exploration of heart rate measures as approximations of cognitive load. It is our goal to determine guidelines for future autonomy and interaction designers such that their systems will reduce cognitive load and increase the level of trust in robot teammates. This is an initial experiment that uses the least amount of vehicles yet still gathers competitive data on the water. Future experiments will increase in complexity to many opponents and many teammates.

Inferring Social Structure of Animal Groups from Tracking Data

Inferring the social structures of animal groups from their observed behavior is a non-trivial task usually handled by direct observation. Recent advances in sensing and tracking technology have enabled the collection of dense spatial data over long periods of time automatically. The qualitative differences between sparse hand-coded data and dense tracking data necessitate a new approach to inferring the social structure of the observed animals. We present a framework for using agent-based simulations to guide our approach to inferring social structure from tracking data collected from a small group of rhesus macaques over a period of three months. As part of this framework, we describe a version of the DOMWORLD model of dominance interactions in rhesus macaques that has been modified to include association preference, and adapted to more closely match the environment where the monkeys were housed. An exploration of simulation results reveals important characteristics of the tracking data. The inferred social structures of the tracked monkeys are also presented.