No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Enabling robust human-robot cooperation through flexible fully Bayesian shared sensing
Abstract
Cooperative human-robot sensing has the potential to overcome many hurdles for networked field robotic applications, especially those with significant sensing, computational or communication constraints that make teleoperation or direct supervisory control difficult. The main idea is to augment robotic sensing horizons with the diverse and complementary capabilities of 'human sensors' for solving difficult hybrid nonlinear state estimation and perception problems, although robots may still plan and control their own actions autonomously. In this work, we examine two related issues through the use of sketch-based and semantic codebook perceptual interfaces for probabilistic target search problems: (i) how should autonomous machines/robots assess the trustworthiness of human sensors?; (ii) what strategies can be used to generate human-machine 'dialog' about complex uncertainties in random variables, without cognitively overburdening humans or undermining human trust in automation? Copyright © 2014, Association for the Advancement of Artificial Intelligence. All rights reserved.
This paper presents a natural framework for information sharing in cooperative tasks involving humans and robots. In this framework, all information gathered over time by a human–robot team is exchanged and summarized in the form of a fused probability density function (pdf). An approach for an intelligent system to describe its belief pdfs in English expressions is presented. This belief expression generation is achieved through two goodness measures: semantic correctness and information preservation. In order to describe complex, multimodal belief pdfs, a Mixture of Statements (MoS) model is proposed such that optimal expressions can be generated through compositions of multiple statements. The model is further extended to a nonparametric Dirichlet process MoS generation, such that the optimal number of statements required for describing a given pdf is automatically determined. Results based on information loss, human collaborative task performances, and correctness rating scores suggest that the proposed method for generating belief expressions is an effective approach for communicating probabilistic information between robots and humans.
This paper considers Bayesian data fusion of con-ventional robot sensor information with ambiguous human-generated categorical information about continuous world states of interest. First, it is shown that such soft information can be generally modeled via hybrid continuous-to-discrete likelihoods based on the softmax function. A new hybrid fusion procedure, called variational Bayesian importance sampling (VBIS), is then introduced to combine the strengths of variational Bayes approximations and fast Monte Carlo methods to produce reliable posterior estimates for Gaussian priors and softmax likelihoods. VBIS is then extended to more general fusion problems involving complex Gaussian mixture (GM) priors and multimodal softmax likelihoods, leading to accurate GM approximations of highly non-Gaussian fusion posteriors for a wide range of robot sensor data and soft human data. Experiments for hardware-based mul-titarget search missions with a cooperative human-autonomous robot team show that humans can serve as highly informative sensors through proper data modeling and fusion, and that VBIS provides reliable and scalable Bayesian fusion estimates via GMs.
In this paper, scalable collaborative human-robot systems for information gathering applications are approached as a decentralized Bayesian sensor network problem. Human-computer augmented nodes and autonomous mobile sensor platforms are collaborating on a peer-to-peer basis by sharing information via wireless communication network. For each node, a computer (onboard the platform or carried by the human) implements both a decentralized Bayesian data fusion algorithm and a decentralized Bayesian control negotiation algorithm. The individual node controllers iteratively negotiate anonymously with each other in the information space to find cooperative search plans based on both observed and predicted information that explicitly consider the platforms (humans and robots) motion models, their sensors detection functions, as well as the target arbitrary motion model. The results of a collaborative multi-target search experiment conducted with a team of four autonomous mobile sensor platforms and five humans carrying small portable computers with wireless communication are presented to demonstrate the efficiency of the approach.
Collaborative control is a teleoperation system model based on human–robot dialogue. With this model, the robot asks questions to the human in order to obtain assistance with cognition and perception. This enables the human to function as a resource for the robot and help to compensate for limitations of autonomy. To understand how collaborative control influences human–robot interaction, we performed a user study based on contextual inquiry (CI). The study revealed that: (1) dialogue helps users understand problems encountered by the robot and (2) human assistance is a limited resource that must be carefully managed.
Humans and robots need to exchange information if the objective is to achieve a task cooperatively. Two questions are considered in this paper: what type of information to communicate, and how to cope with the limited resources of human operators. Decision-theoretic human-robot communication can provide answers to both questions: the type of information is determined by the underlying probabilistic representation, and value-of-information theory helps decide when it is appropriate to query operators for information. A robot navigation task is used to evaluate the system by comparing it to conventional teleoperation. The results of a user study show that the developed system is superior with respect to performance, operator workload, and usability.
The Autonomous City Explorer (ACE) project combines research from autonomous outdoor navigation and human-robot interaction. The ACE robot is capable of navigating unknown urban environments without the use of GPS data or prior map knowledge. It finds its
way by interacting with pedestrians in a natural and intuitive way and building a topological representation of its surroundings.
In a recent experiment the robot managed to successfully travel a 1.5 km distance from the campus of the Technische Universität
München to Marienplatz, the central square of Munich. This article describes the principles and system components for navigation
in urban environments, information retrieval through natural human-robot interaction, the construction of a suitable semantic
representation as well as results from the field experiment.
The Dezert–Smarandache theory (DSmT) and transferable belief model (TBM) both address concerns with the Bayesian methodology as applied to applications involving the fusion of uncertain, imprecise and conflicting information. In this paper, we revisit these concerns regarding the Bayesian methodology in the light of recent developments in the context of the DSmT and TBM. We show that, by exploiting recent advances in the Bayesian research arena, one can devise and analyse Bayesian models that have the same emergent properties as DSmT and TBM. Specifically, we define Bayesian models that articulate uncertainty over the value of probabilities (including multimodal distributions that result from conflicting information) and we use a minimum expected cost criterion to facilitate making decisions that involve hypotheses that are not mutually exclusive. We outline our motivation for using the Bayesian methodology and also show that the DSmT and TBM models are computationally expedient approaches to achieving the same endpoint. Our aim is to provide a conduit between these two communities such that an objective view can be shared by advocates of all the techniques.
This paper presents the design of a probabilistic model of human perception as an integral part of a decentralized data fusion system. The system consists of a team of human operators and robotic platforms, together forming a heterogeneous sensor network. Human operators are regarded as information sources submitting raw observations. The observations are converted into a probabilistic representation suitable for fusion with the system's belief. The conversion is performed by a human sensor model (HSM). The initial HSM is built offline based on an average of multiple human subjects conducting a calibration experiment. Since individual human operators may vary in their performance, an online adaptation of the HSM is required. The network estimate is used for adaptation because the true feature state is unknown at runtime. Results of an outdoor calibration experiment using range and bearing observations are presented. Simulations show the feasibility of efficient online adaptation.