Robot navigation in dense crowds : statistical models and experimental studies of human robot cooperation

This thesis explores the problem of mobile robot navigation in dense human crowds. We begin by considering a fundamental impediment to classical motion planning algorithms called the freezing robot problem: once the environment surpasses a certain level of complexity, the planner decides that all forward paths are unsafe, and the robot freezes in place (or performs unnecessary maneuvers) to avoid collisions. Since a feasible path typically exists, this behavior is suboptimal. Existing approaches have focused on reducing predictive uncertainty by employing higher fidelity individual dynamics models or heuristically limiting the individual predictive covariance to prevent overcautious navigation. We demonstrate that both the individual prediction and the individual predictive uncertainty have little to do with this undesirable navigation behavior. Additionally, we provide evidence that dynamic agents are able to navigate in dense crowds by engaging in joint collision avoidance, cooperatively making room to create feasible trajectories. We accordingly develop interacting Gaussian processes, a prediction density that captures cooperative collision avoidance, and a "multiple goal" extension that models the goal driven nature of human decision making. Navigation naturally emerges as a statistic of this distribution.

Most importantly, we empirically validate our models in the Chandler dining hall at Caltech during peak hours, and in the process, carry out the first extensive quantitative study of robot navigation in dense human crowds (collecting data on 488 runs). The multiple goal interacting Gaussian processes algorithm performs comparably with human teleoperators in crowd densities nearing 1 person/m², while a state of the art noncooperative planner exhibits unsafe behavior more than 3 times as often as the multiple goal extension, and twice as often as the basic interacting Gaussian process approach. Furthermore, a reactive planner based on the widely used dynamic window approach proves insufficient for crowd densities above 0.55 people/m². We also show that our noncooperative planner or our reactive planner capture the salient characteristics of nearly any dynamic navigation algorithm. For inclusive validation purposes, we show that either our non-interacting planner or our reactive planner captures the salient characteristics of nearly any existing dynamic navigation algorithm. Based on these experimental results and theoretical observations, we conclude that a cooperation model is critical for safe and efficient robot navigation in dense human crowds.

Finally, we produce a large database of ground truth pedestrian crowd data. We make this ground truth database publicly available for further scientific study of crowd prediction models, learning from demonstration algorithms, and human robot interaction models in general.

Building a software architecture for a human-robot team using the ORCA framework

This paper considers the problem of building a software architecture for a human-robot team. The objective of the team is to build a multi-attribute map of the world by performing information fusion. A decentralized approach to information fusion is adopted to achieve the system properties of scalability and survivability. Decentralization imposes constraints on the design of the architecture and its implementation. We show how a Component-Based Software Engineering approach can address these constraints. The architecture is implemented using Orca – a component-based software framework for robotic systems. Experimental results from a deployed system comprised of an unmanned air vehicle, a ground vehicle, and two human operators are presented. A section on the lessons learned is included which may be applicable to other distributed systems with complex algorithms. We also compare Orca to the Player software framework in the context of distributed systems.

The effect of autonomy transparency in human-robot interactions : a preliminary study on operator cognitive workload and situation awareness in multiple heterogeneous UAV management

The autonomous capabilities in collaborative unmanned aircraft systems are growing rapidly. Without appropriate transparency, the effectiveness of the future multiple Unmanned Aerial Vehicle (UAV) management paradigm will be significantly limited by the human agent’s cognitive abilities; where the operator’s CognitiveWorkload (CW) and Situation Awareness (SA) will present as disproportionate. This proposes a challenge in evaluating the impact of robot autonomous capability feedback, allowing the human agent greater transparency into the robot’s autonomous status - in a supervisory role. This paper presents; the motivation, aim, related works, experiment theory, methodology, results and discussions, and the future work succeeding this preliminary study. The results in this paper illustrates that, with a greater transparency of a UAV’s autonomous capability, an overall improvement in the subjects’ cognitive abilities was evident, that is, with a confidence of 95%, the test subjects’ mean CW was demonstrated to have a statistically significant reduction, while their mean SA was demonstrated to have a significant increase.

Workspace comparisons of setup configurations for human-robot interaction

In virtual assembly verification or remote maintenance tasks, bimanual haptic interfaces play a crucial role in successful task completion. This paper proposes a method for objectively comparing how well a haptic interface covers the reachable workspace of human arms. Two system configurations are analyzed for a recently introduced haptic device that is based on two DLR-KUKA light weight robots: the standard configuration, where the device is opposite the human operator, and the ergonomic configuration, where the haptic device is mounted behind the human operator. The human operator directly controls the robotic arms using handles. The analysis is performed using a representation of the robot arm workspace. The merits of restricting the comparisons to the most significant regions of the human workspace are discussed. Using this method, a greater workspace correspondence for the ergonomic configuration was shown. ©2010 IEEE.

Manufacturing System Simulation & Human Robot Interaction in VR:Manufacturing system simulation: Methodologies, software tools, case study in transportation design

Virtual Reality techniques are relatively new, having experienced significant development only during the last few years, in accordance with the progress achieved by computer science and hardware and software technologies. The study of such advanced design systems has led to the realization of an immersive environment in which new procedures for the evaluation of product prototypes, ergonomics and manufacturing operations have been simulated. The application of the environment realized to robotics, ergonomics, plant simulations and maintainability verifications has allowed us to highlight the advantages offered by a design methodology: the possibility of working on the industrial product in the first phase of conception; of placing the designer in front of the virtual reproduction of the product in a realistic way; and of interacting with the same concept. The aim of this book is to present an updated vision of VM through different aspects. We will describe the trends and results achieved in the automotive, aerospace and railway fields, in terms of the Digital Product Creation Process to design the product and the manufacturing process.

Development of advanced human robot interaction systems

O trabalho aqui apresentado é a Dissertação da minha Tese do curso de Mestrado em Engenharia Eletrotécnica e de Computadores do ISEP, realizada em parceria com o INESC TEC. O trabalho consiste no desenvolvimento de um sistema avançado de interação entre homem-robô, usando ferramentas de software livres e de domínio público e hardware pouco dispendioso e facilmente acessível. Pretende-se que o sistema desenvolvido possa ser adotado por pequenas ou micro empresas, daí a restrição monetária. Este tipo de empresas tem, por norma, uma capacidade de investimento pequena, e ficam impossibilitadas de aceder a este tipo de sistemas automatizados se estes forem caros. No entanto, o robô continua a ser um componente fundamental, sendo dispendioso. Os trabalhos realizados pelos sistemas robóticos podem por um lado, ser repetitivos sem necessidade de grandes ajustes; por outro lado, o trabalho a realizar pode ser bastante diverso, sendo necessários bastantes ajustes com (possivelmente) programação do robô. As empresas podem não ter disponível mão-de-obra qualificada para realização da programação do robô. Pretende-se então um sistema de “ensino” que seja simples e rápido. Este trabalho pretende satisfazer as necessidades de um sistema de interação homem-robô intuitivo mesmo para operadores que não estejam familiarizados com a robótica. Para simplificar a transferência de informação da tarefa a desempenhar pelo sistema robótico é usado um sistema de infravermelhos para delinear a operação a desempenhar, neste caso concreto uma operação de soldadura. O operador usa um apontador com marcadores, a posição destes marcadores é detetada usando duas câmaras para permitir o posicionamento tridimensional no espaço. As câmaras possuem filtros infravermelhos para separar o espectro de luz. Para o controlo do sistema e interface com o robô é usado um computador de baixos recursos computacionais e energéticos, e também de baixo custo. O sistema desenvolvido é portanto computacionalmente leve para poder ser executado neste computador.

Heterogeneous Multi-Robot Cooperation

This report addresses the problem of achieving cooperation within small- to medium- sized teams of heterogeneous mobile robots. I describe a software architecture I have developed, called ALLIANCE, that facilitates robust, fault tolerant, reliable, and adaptive cooperative control. In addition, an extended version of ALLIANCE, called L-ALLIANCE, is described, which incorporates a dynamic parameter update mechanism that allows teams of mobile robots to improve the efficiency of their mission performance through learning. A number of experimental results of implementing these architectures on both physical and simulated mobile robot teams are described. In addition, this report presents the results of studies of a number of issues in mobile robot cooperation, including fault tolerant cooperative control, adaptive action selection, distributed control, robot awareness of team member actions, improving efficiency through learning, inter-robot communication, action recognition, and local versus global control.

3D path planning with novel multiple 2D layered approach for complex human-robot interaction

Navigating cluttered indoor environments is a difficult problem in indoor service robotics. The Acroboter concept, a novel approach to indoor locomotion, represents unique opportunity to avoid obstacles in indoor environments by navigating the ceiling plane. This mode of locomotion requires the ability to accurately detect obstacles, and plan 3D trajectories through the environment. This paper presents the development of a resilient object tracking system, as well as a novel approach to generating 3D paths suitable for such robot configurations. Distributed human-machine interfacing allowing simulation previewing of actions is also considered in the developed system architecture.