• Corpus ID: 239024774

Probabilistic Semantic Data Association for Collaborative Human-Robot Sensing

@article{Wakayama2021ProbabilisticSD,
  title={Probabilistic Semantic Data Association for Collaborative Human-Robot Sensing},
  author={Shohei Wakayama and Nisar Ahmed},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.09621}
}
In collaborative human-robot semantic sensing problems, e.g. for scientific exploration, robots could potentially overtrust information given by a human partner, resulting in suboptimal state estimation and poor team performance. When humans cannot be treated as oracles, robots need to update state beliefs to correctly account for possible discrepancies between human semantic observations and the actual world states which lead to those observations. This work develops strategies for rigorous… 

References

SHOWING 1-10 OF 40 REFERENCES
Fully bayesian learning and spatial reasoning with flexible human sensor networks
TLDR
Hierarchical Bayesian models and centralized inference strategies based on Gibbs sampling are proposed to address 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.
Bayesian Multicategorical Soft Data Fusion for Human–Robot Collaboration
TLDR
Experiments for hardware-based multitarget 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.
Collaborative Semantic Data Fusion with Dynamically Observable Decision Processes
  • Luke Burks, N. Ahmed
  • Computer Science
    2019 22th International Conference on Information Fusion (FUSION)
  • 2019
TLDR
A new Dynamically Observable Monte Carlo planning (DOMCP) algorithm is developed as an efficient means for updating online sampling-based planning policies for POMDPs with non-static observation models.
Autonomous Localization of an Unknown Number of Targets Without Data Association Using Teams of Mobile Sensors
  • P. Dames, Vijay R. Kumar
  • Engineering, Computer Science
    IEEE Transactions on Automation Science and Engineering
  • 2015
TLDR
This paper seeks to address the problem of automating this data collection process, so that a team of mobile sensor platforms are able to autonomously explore a given environment in order to determine the number of objects of interest and their locations, while avoiding any explicit data association.
Information fusion in human-robot collaboration using neural network representation
TLDR
An algorithm for hard andsoft data fusion is developed for tracking moving objects using hard data from sensors on autonomous agents and soft data from human observations and yields consistent fused estimates in the absence of unknown correlations between state estimates obtained using human measurements and robot sensor measurements.
Using humans as sensors in robotic search
TLDR
The human role as sensor is illustrated referencing results of an earlier experiment investigating human performance of operator, navigator, or “perceptual sensor” tasks for teams of 4, 8, and 12 simulated pioneer P3AT robots.
Multi-modal active perception for information gathering in science missions
TLDR
This paper presents an active perception approach that aims to reduce robots’ reliance on human supervision and improve science productivity by encoding scientists’ domain knowledge and decision making process on-board by presenting a Bayesian network architecture to compactly model critical aspects of scientific knowledge while remaining robust to observation and modeling uncertainty.
Adaptive human sensor model in sensor networks
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
Optimal Continuous State POMDP Planning With Semantic Observations: A Variational Approach
TLDR
Novel strategies for optimal planning with semantic observations using continuous state partially observable Markov decision processes (CPOMDPs) are developed, including the derivation of closed-form variational Bayes GM approximations of point-based value iteration Bellman policy backups, using softmax models of continuous-discrete semantic observation probabilities.
On truth discovery in social sensing: A maximum likelihood estimation approach
TLDR
The approach is shown to outperform the state of the art fact-finding heuristics, as well as simple baselines such as majority voting, and to offer the first optimal solution to the above truth discovery problem.
...
1
2
3
4
...