An Experimental Evaluation of Bayesian Soft Human Sensor Fusion in Robotic Systems

Sample, Eric; Ahmed, Nisar; Campbell, Mark

doi:10.2514/6.2012-4542

Cited by 8 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case where the reference state parameter X l is fixed, the language generation problem reduces to the problem defined by (12)- (13); note that ζ(•) is a deterministic function. This problem formulation can be extended to the case of a more complex K-hypotheses belief expression "The target is <hypothesis 1>, or <hypothesis 2>, or ... , <hypothesis K>," with…”

Section: A Mixture Of Statements (Mos)mentioning

confidence: 99%

“…In previous research [2], [13], a human-to-robot information sharing technique was developed to handle language understanding subproblem involved in step (1) and information fusion subproblem involved in steps (2) and (3) of the information exchange loop. However, the robot's belief generated in (3) is directly communicated to the human audience in its raw format of a pdf.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Human-robot information sharing with structured language generation from probabilistic beliefs

Tse

Campbell

2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

This paper presents a framework for information sharing and fusion in cooperative tasks involving humans and robots. In this context, all information regarding the state of interest is recursively fused and maintained by each agent in a form of belief. For a robot agent, its belief is commonly and practically represented as a probability density function (pdf), formed by traditional sensor fusion and state estimation algorithms. In cooperative tasks with non-expert humans, a robot needs to effectively communicate its belief so that the gathered information can be easily processed and interpreted by the humans. The goal of this research is to provide twoway information exchange and fusion between robots and humans, the former operating on pdfs, while the latter on English sentences. This is achieved by considering two goodness measures: semantic correctness and information preservation. Based on the goodness measures studied, results show that the proposed framework is able to generate optimal statements describing the given belief pdfs and successfully recover the initial inputs used to generate them. Additionally, in order to describe complex belief pdfs, a Mixture of Statements (MoS) model is proposed such that the optimal expression can be generated through a composition of more than one statements. With a nonparametric Dirichlet Process MoS generation, it is found that the robot can determine correctly the number of statements as well as the corresponding reference parameters needed to describe all hypotheses underlying its belief.

show abstract

Section: A Mixture Of Statements (Mos)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Human-robot information sharing with structured language generation from probabilistic beliefs

Tse

Campbell

2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, these techniques are based on structured verbal communication interfaces that can fail to adequately capture the intended meaning of a human observation, especially in large unstructured or featureless environments, e.g. outdoor spaces [22]. Furthermore, these techniques assume that human sensor models are perfectly known and obtainable via offline calibration, which can be very time-consuming and is not robust to unanticipated semantic context shifts.…”

Section: Introductionmentioning

confidence: 96%

“…Approaches based on semantic codebook likelihood models, such as the ones proposed in [2,19], are generally effective and allow users to supply useful information via simple high-level language. However, they can lead to suboptimal fusion results and user frustration in actual spatial state estimation applications, since all soft observations about the continuous target state space must be expressed via finite semantic dictionaries and structured synatx, which may not adequately cover or succinctly describe all possible spatial target configurations [22]. While it is always possible to resort to more sophisticated interfaces or natural language processing techniques to account for such cases, in practice this increases the complexity of the user interface and fusion problem, and can make learning of p(ζ i k |X) significantly more difficult.…”

Section: Introductionmentioning

confidence: 99%

Fully bayesian learning and spatial reasoning with flexible human sensor networks

Ahmed

Campbell

Casbeer³

et al. 2015

Proceedings of the ACM/IEEE Sixth International Conference on Cyber-Physical Systems

Self Cite

View full text Add to dashboard Cite

This work considers the challenging problem of simultaneous modeling and fusion of 'soft data' generated by a network of 'human sensors' for spatial state estimation tasks, such as lost target search or large area surveillance. Human sensors can opportunistically provide useful information to constrain difficult state estimation problems, but are imperfect information sources whose reliability cannot be easily determined in advance. Formal observation likelihood models are derived for flexible sketch-based observations, but are found to lead to analytically intractable statistical dependencies between unknown sensor parameters and spatial states of interest that cannot adequately characterized by simple point estimates. Hierarchical Bayesian models and centralized inference strategies based on Gibbs sampling are proposed to address these issues, especially in cases of sparse, noisy, ambiguous and conflicting soft data. This leads to an automatic online calibration procedure for human sensor networks, as well as conservative spatial state posteriors that naturally account for model uncertainties. Experimental outdoor target search results with real spatial human sensor data (obtained via networked mobile graphical sketch interfaces) demonstrate the proposed methodology.

show abstract

A touch interface for soft data modeling in Bayesian estimation

Mehta

McCourt

Doucette

et al. 2014

2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

An Experimental Evaluation of Bayesian Soft Human Sensor Fusion in Robotic Systems

Cited by 8 publications

References 16 publications

Human-robot information sharing with structured language generation from probabilistic beliefs

Human-robot information sharing with structured language generation from probabilistic beliefs

Fully bayesian learning and spatial reasoning with flexible human sensor networks

A touch interface for soft data modeling in Bayesian estimation

Contact Info

Product

Resources

About