Empirical Estimates on Hand Manipulation are Recoverable: A Step Towards Individualized and Explainable Robotic Support in Everyday Activities

@article{Wich2022EmpiricalEO,
  title={Empirical Estimates on Hand Manipulation are Recoverable: A Step Towards Individualized and Explainable Robotic Support in Everyday Activities},
  author={Alexander Wich and Holger Schultheis and Michael Beetz},
  journal={ArXiv},
  year={2022},
  volume={abs/2201.11824}
}
A key challenge for robotic systems is to figure out the behavior of another agent. The capability to draw correct inferences is crucial to derive human behavior from examples. Processing correct inferences is especially challenging when (confounding) factors are not controlled experimentally (observational evidence). For this reason, robots that rely on inferences that are correlational risk a biased interpretation of the evidence. We propose equipping robots with the necessary tools to… 
[PDF] Semantic Reader

Figures and Tables from this paper

References

SHOWING 1-10 OF 38 REFERENCES

The Robot as Scientist: Using Mental Simulation to Test Causal Hypotheses Extracted from Human Activities in Virtual Reality

This paper introduces a novel learning method for extracting instrumental dependencies by following the scientific approach of observations, generation of causal hypotheses, and testing through experiments, using a virtual reality dataset containing observations from human activities to generate hypotheses about causal dependencies between actions.

Using Causal Analysis to Learn Specifications from Task Demonstrations

This work shows that it is possible to learn a generative model for distinct user behavioral types, extracted from human demonstrations, by enforcing clustering of preferred task solutions within the latent space, and uses this model to differentiate between user types and to find cases with overlapping solutions.

A survey of robot learning from demonstration

Know Rob 2.0 — A 2nd Generation Knowledge Processing Framework for Cognition-Enabled Robotic Agents

Novel features and extensions of KnowRob2 substantially increase the capabilities of robotic agents of acquiring open-ended manipulation skills and competence, reasoning about how to perform manipulation actions more realistically, and acquiring commonsense knowledge.

Learning Motion Parameterizations of Mobile Pick and Place Actions from Observing Humans in Virtual Environments

An approach and an implemented pipeline for transferring data acquired from observing humans in virtual environments onto robots acting in the real world, and adapting the data accordingly to achieve successful task execution are presented.

Developmental Robotics and its Role Towards Artificial General Intelligence

Developmental Robotics seeks to investigate and model cognitively plausible inductive biases including curiosity, homeostasis and body schemas and shows that the computational models for continual learning do not only improve robots and deliver empirical foundations to better understand intelligent behavior.

Perspectives on Sim2Real Transfer for Robotics: A Summary of the R: SS 2020 Workshop

This report presents the debates, posters, and discussions of the Sim2Real workshop held in conjunction with the 2020 edition of the "Robotics: Science and System" conference. Twelve leaders of the…

Learning like a baby: a survey of artificial intelligence approaches

  • Frank Guerin
  • Computer Science
    The Knowledge Engineering Review
  • 2011
This survey reviews work in the ‘developmental’ approach to artificial intelligence, with the emphasis on those that focus on early learning, for example, sensorimotor learning.

What drives children’s limb selection for reaching in hemispace?

The findings add to the growing acceptance that limb selection is task and context dependent, rather than a biologically based invariant feature of motor behavior.

Causal learning from probabilistic events in 24-month-olds: an action measure.

The results demonstrate that toddlers can learn about cause and effect without trial-and-error or linguistic instruction on the task, simply by observing the probabilistic patterns of evidence resulting from the imperfect actions of other social agents.