Search Results for author: Sonia Chernova

Found 31 papers, 10 papers with code

Proactive Robot Assistance via Spatio-Temporal Object Modeling

1 code implementation28 Nov 2022 Maithili Patel, Sonia Chernova

Proactive robot assistance enables a robot to anticipate and provide for a user's needs without being explicitly asked.

Temporal Sequences

StructDiffusion: Object-Centric Diffusion for Semantic Rearrangement of Novel Objects

no code implementations8 Nov 2022 Weiyu Liu, Tucker Hermans, Sonia Chernova, Chris Paxton

Robots operating in human environments must be able to rearrange objects into semantically-meaningful configurations, even if these objects are previously unseen.

Explainable Knowledge Graph Embedding: Inference Reconciliation for Knowledge Inferences Supporting Robot Actions

1 code implementation4 May 2022 Angel Daruna, Devleena Das, Sonia Chernova

Results from our algorithmic evaluation affirm our model design choices, and the results of our user studies with non-experts support the need for the proposed inference reconciliation framework.

Decision Making Knowledge Graph Embedding

Creative Problem Solving in Artificially Intelligent Agents: A Survey and Framework

no code implementations21 Apr 2022 Evana Gizzi, Lakshmi Nair, Sonia Chernova, Jivko Sinapov

Creative Problem Solving (CPS) is a sub-area within Artificial Intelligence (AI) that focuses on methods for solving off-nominal, or anomalous problems in autonomous systems.

Subgoal-Based Explanations for Unreliable Intelligent Decision Support Systems

no code implementations11 Jan 2022 Devleena Das, Been Kim, Sonia Chernova

Intelligent decision support (IDS) systems leverage artificial intelligence techniques to generate recommendations that guide human users through the decision making phases of a task.

Decision Making

Incremental Object Grounding Using Scene Graphs

no code implementations6 Jan 2022 John Seon Keun Yi, Yoonwoo Kim, Sonia Chernova

This paper aims to disambiguate the human's referring expressions by allowing the agent to ask relevant questions based on semantic data obtained from scene graphs.

Semantic-Based Explainable AI: Leveraging Semantic Scene Graphs and Pairwise Ranking to Explain Robot Failures

no code implementations8 Aug 2021 Devleena Das, Sonia Chernova

Our framework autonomously captures the semantic information in a scene to produce semantically descriptive explanations for everyday users.

Explainable Activity Recognition for Smart Home Systems

no code implementations20 May 2021 Devleena Das, Yasutaka Nishimura, Rajan P. Vivek, Naoto Takeda, Sean T. Fish, Thomas Ploetz, Sonia Chernova

Finally, we show that explanations generated by some XAI methods can lead users to lose confidence in the accuracy of the underlying activity recognition model, while others lead users to gain confidence.

Activity Recognition Explainable artificial intelligence

Towards Robust One-shot Task Execution using Knowledge Graph Embeddings

no code implementations10 May 2021 Angel Daruna, Lakshmi Nair, Weiyu Liu, Sonia Chernova

We validated the approach on a physical platform, which resulted in the successful generalization of initial task plans to 38 of 50 execution environments with errors resulting from autonomous robot operation included.

Knowledge Graph Embeddings

Continual Learning of Knowledge Graph Embeddings

1 code implementation14 Jan 2021 Angel Daruna, Mehul Gupta, Mohan Sridharan, Sonia Chernova

In recent years, there has been a resurgence in methods that use distributed (neural) representations to represent and reason about semantic knowledge for robotics applications.

Continual Learning Knowledge Graph Embedding +2

Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recovery

no code implementations5 Jan 2021 Devleena Das, Siddhartha Banerjee, Sonia Chernova

In order for error explanations to be meaningful, we investigate what types of information within a set of hand-scripted explanations are most helpful to non-experts for failure and solution identification.

Decision Making

Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees

no code implementations24 Dec 2020 M. Asif Rana, Anqi Li, Dieter Fox, Sonia Chernova, Byron Boots, Nathan Ratliff

The policy structure provides the user an interface to 1) specifying the spaces that are directly relevant to the completion of the tasks, and 2) designing policies for certain tasks that do not need to be learned.

Bi-directional Domain Adaptation for Sim2Real Transfer of Embodied Navigation Agents

no code implementations24 Nov 2020 Joanne Truong, Sonia Chernova, Dhruv Batra

Simulation offers the ability to train large numbers of robots in parallel, and offers an abundance of data.

Domain Adaptation PointGoal Navigation Robotics

Explainable AI for System Failures: Generating Explanations that Improve Human Assistance in Fault Recovery

no code implementations18 Nov 2020 Devleena Das, Siddhartha Banerjee, Sonia Chernova

With the growing capabilities of intelligent systems, the integration of artificial intelligence (AI) and robots in everyday life is increasing.

Multimodal Material Classification for Robots using Spectroscopy and High Resolution Texture Imaging

1 code implementation2 Apr 2020 Zackory Erickson, Eliot Xing, Bharat Srirangam, Sonia Chernova, Charles C. Kemp

Finally, we present how a robot can combine this high resolution local sensing with images from the robot's head-mounted camera to achieve accurate material classification over a scene of objects on a table.

General Classification Material Classification +1

Leveraging Rationales to Improve Human Task Performance

no code implementations11 Feb 2020 Devleena Das, Sonia Chernova

Machine learning (ML) systems across many application areas are increasingly demonstrating performance that is beyond that of humans.

BIG-bench Machine Learning Game of Chess

Tool Substitution with Shape and Material Reasoning Using Dual Neural Networks

no code implementations11 Nov 2019 Nithin Shrivatsav, Lakshmi Nair, Sonia Chernova

This paper explores the problem of tool substitution, namely, identifying substitute tools for performing a task from a given set of candidate tools.

CAGE: Context-Aware Grasping Engine

1 code implementation24 Sep 2019 Weiyu Liu, Angel Daruna, Sonia Chernova

Semantic grasping is the problem of selecting stable grasps that are functionally suitable for specific object manipulation tasks.


Active Learning within Constrained Environments through Imitation of an Expert Questioner

no code implementations1 Jul 2019 Kalesha Bullard, Yannick Schroecker, Sonia Chernova

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives.

Active Learning Imitation Learning

Leveraging Semantics for Incremental Learning in Multi-Relational Embeddings

no code implementations29 May 2019 Angel Daruna, Weiyu Liu, Zsolt Kira, Sonia Chernova

Service robots benefit from encoding information in semantically meaningful ways to enable more robust task execution.

Incremental Learning Knowledge Graphs

Path Ranking with Attention to Type Hierarchies

1 code implementation26 May 2019 Weiyu Liu, Angel Daruna, Zsolt Kira, Sonia Chernova

The objective of the knowledge base completion problem is to infer missing information from existing facts in a knowledge base.

Knowledge Base Completion Knowledge Graphs

RoboCSE: Robot Common Sense Embedding

no code implementations24 Mar 2019 Angel Daruna, Weiyu Liu, Zsolt Kira, Sonia Chernova

Autonomous service robots require computational frameworks that allow them to generalize knowledge to new situations in a manner that models uncertainty while scaling to real-world problem sizes.

Common Sense Reasoning

Unbiasing Semantic Segmentation For Robot Perception using Synthetic Data Feature Transfer

no code implementations11 Sep 2018 Jonathan C Balloch, Varun Agrawal, Irfan Essa, Sonia Chernova

We show that pretraining real-time segmentation architectures with synthetic segmentation data instead of ImageNet improves fine-tuning performance by reducing the bias learned in pretraining and closing the \textit{transfer gap} as a result.

Image Segmentation Semantic Segmentation

Classification of Household Materials via Spectroscopy

2 code implementations10 May 2018 Zackory Erickson, Nathan Luskey, Sonia Chernova, Charles C. Kemp

To explore this, we collected a dataset of spectral measurements from two commercially available spectrometers during which a robotic platform interacted with 50 flat material objects, and we show that a neural network model can accurately analyze these measurements.

Classification General Classification +2

Action Categorization for Computationally Improved Task Learning and Planning

no code implementations26 Apr 2018 Lakshmi Nair, Sonia Chernova

This paper explores the problem of task learning and planning, contributing the Action-Category Representation (ACR) to improve computational performance of both Planning and Reinforcement Learning (RL).

reinforcement-learning Reinforcement Learning (RL) +1

Semi-Supervised Haptic Material Recognition for Robots using Generative Adversarial Networks

1 code implementation10 Jul 2017 Zackory Erickson, Sonia Chernova, Charles C. Kemp

Our approach achieves state-of-the-art results and enables a robot to estimate the material class of household objects with ~90% accuracy when 92% of the training data are unlabeled.

Material Recognition Time Series Analysis

Situated Structure Learning of a Bayesian Logic Network for Commonsense Reasoning

no code implementations1 Jul 2016 Haley Garrison, Sonia Chernova

This paper details the implementation of an algorithm for automatically generating a high-level knowledge network to perform commonsense reasoning, specifically with the application of robotic task repair.

Interactive Policy Learning through Confidence-Based Autonomy

no code implementations15 Jan 2014 Sonia Chernova, Manuela Veloso

We present Confidence-Based Autonomy (CBA), an interactive algorithm for policy learning from demonstration.

Cannot find the paper you are looking for? You can Submit a new open access paper.