Multimodal Coherent Explanation Generation of Robot Failures
- URL: http://arxiv.org/abs/2410.00659v1
- Date: Tue, 1 Oct 2024 13:15:38 GMT
- Title: Multimodal Coherent Explanation Generation of Robot Failures
- Authors: Pradip Pramanick, Silvia Rossi,
- Abstract summary: We introduce an approach to generate coherent multimodal explanations by checking the logical coherence of explanations from different modalities.
Our experiments suggest that fine-tuning a neural network that was pre-trained to recognize textual entailment, performs well for coherence assessment.
- Score: 1.3965477771846408
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The explainability of a robot's actions is crucial to its acceptance in social spaces. Explaining why a robot fails to complete a given task is particularly important for non-expert users to be aware of the robot's capabilities and limitations. So far, research on explaining robot failures has only considered generating textual explanations, even though several studies have shown the benefits of multimodal ones. However, a simple combination of multiple modalities may lead to semantic incoherence between the information across different modalities - a problem that is not well-studied. An incoherent multimodal explanation can be difficult to understand, and it may even become inconsistent with what the robot and the human observe and how they perform reasoning with the observations. Such inconsistencies may lead to wrong conclusions about the robot's capabilities. In this paper, we introduce an approach to generate coherent multimodal explanations by checking the logical coherence of explanations from different modalities, followed by refinements as required. We propose a classification approach for coherence assessment, where we evaluate if an explanation logically follows another. Our experiments suggest that fine-tuning a neural network that was pre-trained to recognize textual entailment, performs well for coherence assessment of multimodal explanations. Code & data: https://pradippramanick.github.io/coherent-explain/.
Related papers
- Enhancing Explainability with Multimodal Context Representations for Smarter Robots [0.0]
Key issue in Human-Robot Interaction is enabling robots to effectively perceive and reason over multimodal inputs, such as audio and vision.
We propose a generalized and explainable multimodal framework for context representation, designed to improve the fusion of speech and vision modalities.
arXiv Detail & Related papers (2025-02-28T13:36:47Z) - RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis [102.1876259853457]
We propose a tree-structured multimodal code generation framework for generalized robotic behavior synthesis, termed RoboCodeX.
RoboCodeX decomposes high-level human instructions into multiple object-centric manipulation units consisting of physical preferences such as affordance and safety constraints.
To further enhance the capability to map conceptual and perceptual understanding into control commands, a specialized multimodal reasoning dataset is collected for pre-training and an iterative self-updating methodology is introduced for supervised fine-tuning.
arXiv Detail & Related papers (2024-02-25T15:31:43Z) - Neural Amortized Inference for Nested Multi-agent Reasoning [54.39127942041582]
We propose a novel approach to bridge the gap between human-like inference capabilities and computational limitations.
We evaluate our method in two challenging multi-agent interaction domains.
arXiv Detail & Related papers (2023-08-21T22:40:36Z) - A Closer Look at Reward Decomposition for High-Level Robotic
Explanations [18.019811754800767]
We propose an explainable Q-Map learning framework that combines reward decomposition with abstracted action spaces.
We demonstrate the effectiveness of our framework through quantitative and qualitative analysis of two robotic scenarios.
arXiv Detail & Related papers (2023-04-25T16:01:42Z) - Chaining Simultaneous Thoughts for Numerical Reasoning [92.2007997126144]
numerical reasoning over text should be an essential skill of AI systems.
Previous work focused on modeling the structures of equations, and has proposed various structured decoders.
We propose CANTOR, a numerical reasoner that models reasoning steps using a directed acyclic graph.
arXiv Detail & Related papers (2022-11-29T18:52:06Z) - Evaluating Human-like Explanations for Robot Actions in Reinforcement
Learning Scenarios [1.671353192305391]
We make use of human-like explanations built from the probability of success to complete the goal that an autonomous robot shows after performing an action.
These explanations are intended to be understood by people who have no or very little experience with artificial intelligence methods.
arXiv Detail & Related papers (2022-07-07T10:40:24Z) - Rethinking Explainability as a Dialogue: A Practitioner's Perspective [57.87089539718344]
We ask doctors, healthcare professionals, and policymakers about their needs and desires for explanations.
Our study indicates that decision-makers would strongly prefer interactive explanations in the form of natural language dialogues.
Considering these needs, we outline a set of five principles researchers should follow when designing interactive explanations.
arXiv Detail & Related papers (2022-02-03T22:17:21Z) - Explainable Autonomous Robots: A Survey and Perspective [0.0]
Development of explanatory capabilities is an urgent first step toward autonomous robots.
This survey provides an overview of the various types of "explainability" discussed in machine learning research.
arXiv Detail & Related papers (2021-05-06T13:38:02Z) - Explainable AI for Robot Failures: Generating Explanations that Improve
User Assistance in Fault Recovery [19.56670862587773]
We introduce a new type of explanation, that explains the cause of an unexpected failure during an agent's plan execution to non-experts.
We investigate how such explanations can be autonomously generated, extending an existing encoder-decoder model.
arXiv Detail & Related papers (2021-01-05T16:16:39Z) - Integrating Intrinsic and Extrinsic Explainability: The Relevance of
Understanding Neural Networks for Human-Robot Interaction [19.844084722919764]
Explainable artificial intelligence (XAI) can help foster trust in and acceptance of intelligent and autonomous systems.
NICO, an open-source humanoid robot platform, is introduced and how the interaction of intrinsic explanations by the robot itself and extrinsic explanations provided by the environment enable efficient robotic behavior.
arXiv Detail & Related papers (2020-10-09T14:28:48Z) - Joint Inference of States, Robot Knowledge, and Human (False-)Beliefs [90.20235972293801]
Aiming to understand how human (false-temporal)-belief-a core socio-cognitive ability unify-would affect human interactions with robots, this paper proposes to adopt a graphical model to the representation of object states, robot knowledge, and human (false-)beliefs.
An inference algorithm is derived to fuse individual pg from all robots across multi-views into a joint pg, which affords more effective reasoning inference capability to overcome the errors originated from a single view.
arXiv Detail & Related papers (2020-04-25T23:02:04Z) - A general framework for scientifically inspired explanations in AI [76.48625630211943]
We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented.
This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
arXiv Detail & Related papers (2020-03-02T10:32:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.