AUTO-DISCERN: Autonomous Driving Using Common Sense Reasoning

Kothawade, Suraj; Khandelwal, Vinaya; Basu, Kinjal; Wang, Huaduo; Gupta, Gopal

doi:10.48550/arxiv.2110.13606

Cited by 6 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper follows our earlier research where we advocate a combination of machine learning and commonsense reasoning to carry out intelligent tasks in a human-like manner ( [4,3,19]). In the SQuARE question-answering system ([3]), knowledge was extracted using the Stanford CoreNLP Parser ( [20]) and then mapped to templates from VerbNet.…”

Section: Related Workmentioning

confidence: 99%

Reliable Natural Language Understanding with Large Language Models and Answer Set Programming

Rajasekharan,

Zeng,

Padalkar

et al. 2023

Electron. Proc. Theor. Comput. Sci.

View full text Add to dashboard Cite

Humans understand language by extracting information (meaning) from sentences, combining it with existing commonsense knowledge, and then performing reasoning to draw conclusions. While large language models (LLMs) such as GPT-3 and ChatGPT are able to leverage patterns in the text to solve a variety of NLP tasks, they fall short in problems that require reasoning. They also cannot reliably explain the answers generated for a given question. In order to emulate humans better, we propose STAR, a framework that combines LLMs with Answer Set Programming (ASP). We show how LLMs can be used to effectively extract knowledge-represented as predicates-from language. Goal-directed ASP is then employed to reliably reason over this knowledge. We apply the STAR framework to three different NLU tasks requiring reasoning: qualitative reasoning, mathematical reasoning, and goal-directed conversation. Our experiments reveal that STAR is able to bridge the gap of reasoning in NLU tasks, leading to significant performance improvements, especially for smaller LLMs, i.e., LLMs with a smaller number of parameters. NLU applications developed using the STAR framework are also explainable: along with the predicates generated, a justification in the form of a proof tree can be produced for a given output.

show abstract

Section: Related Workmentioning

confidence: 99%

Reliable Natural Language Understanding with Large Language Models and Answer Set Programming

Rajasekharan,

Zeng,

Padalkar

et al. 2023

Electron. Proc. Theor. Comput. Sci.

View full text Add to dashboard Cite

show abstract

“…An architecture is used for joint scene prediction to explain object-induced actions [149]. An auto-discern system utilises surroundings observations and common-sense reasoning with answers for driving decisions [148].…”

Section: Cases Studiesmentioning

confidence: 99%

Survey on Explainable AI: From Approaches, Limitations and Applications Aspects

Yang

Wei

et al. 2023

Hum-Cent Intell Syst

View full text Add to dashboard Cite

In recent years, artificial intelligence (AI) technology has been used in most if not all domains and has greatly benefited our lives. While AI can accurately extract critical features and valuable information from large amounts of data to help people complete tasks faster, there are growing concerns about the non-transparency of AI in the decision-making process. The emergence of explainable AI (XAI) has allowed humans to better understand and control AI systems, which is motivated to provide transparent explanations for the decisions made by AI. This article aims to present a comprehensive overview of recent research on XAI approaches from three well-defined taxonomies. We offer an in-depth analysis and summary of the status and prospects of XAI applications in several key areas where reliable explanations are urgently needed to avoid mistakes in decision-making. We conclude by discussing XAI’s limitations and future research directions.

show abstract

“…As an exception, the s(CASP) system [2] solves queries without the grounding step and is thus better suited for large domains. It is noteworthy that the s(CASP) system has been used in [9] for automating common sense reasoning for autonomous driving with the help of default rules. However, s(CASP) is a logic programming system, not a universal automated reasoner.…”

Section: Undecidability Grounding and Implementationsmentioning

confidence: 99%

GK: Implementing Full First Order Default Logic for Commonsense Reasoning (System Description)

Tammet

Draheim

Järv

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Our goal is to develop a logic-based component for hybrid – machine learning plus logic – commonsense question answering systems. The paper presents an implementation GK of default logic for handling rules with exceptions in unrestricted first order knowledge bases. GK is built on top of our existing automated reasoning system with confidence calculation capabilities. To overcome the problem of undecidability of checking potential exceptions, GK performs delayed recursive checks with diminishing time limits. These are combined with the taxonomy-based priorities for defaults and numerical confidences.

show abstract

AUTO-DISCERN: Autonomous Driving Using Common Sense Reasoning

Cited by 6 publications

References 16 publications

Reliable Natural Language Understanding with Large Language Models and Answer Set Programming

Reliable Natural Language Understanding with Large Language Models and Answer Set Programming

Survey on Explainable AI: From Approaches, Limitations and Applications Aspects

GK: Implementing Full First Order Default Logic for Commonsense Reasoning (System Description)

Contact Info

Product

Resources

About