Spain

Within the autonomous driving domain, there is now a  clear need and tremendous potential for hybrid solutions (e.g., integrating  semantics, learning, visual computing) towards fulfilling essential  legal and ethical responsibilities involving explainability (e.g.,  for diagnosis), human-centred AI (e.g., interaction design), and industrial  standardisation (e.g, pertaining to representation, realisation  of rules &amp; norms). In these contexts, this highlight paper positions
 recent research from IJCAI 2019 aimed at advancing humancentred  AI principles in the backdrop of the autonomous driving  application domain. From a technical viewpoint, the highlighted research  provides a model for advancing the state of the art in reasoning
 about space and motion, combining reasoning and learning, nonmonotonic  reasoning, and computational modelling of high-level visuospatial  commonsense. In addition to demonstrating the significance  of integrated vision and semantics solutions in autonomous  driving, we also highlight open questions emphasising the need for  interdisciplinary mixed-methods research –involving AI, Psychology,  HCI– to better appreciate the complexity and spectrum of varied
 human-centred challenges in diverse naturalistic driving situations.

ECAI 2020

Driven by Commonsense: On the Role of Human-Centred Visual Explainability for Autonomous Vehicles

standardisation in autonomous driving

human-centred visual sensemaking

answer set programming

autonomous driving

commonsense reasoning

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


ICPR 2020

Within the autonomous driving domain, there is now a  clear need and tremendous potential for hybrid solutions (e.g., integrating  semantics, learning, visual computing) towards fulfilling essential  legal and ethical responsibilities involving explainability (e.g.,  for diagnosis), human-centred AI (e.g., interaction design), and industrial  standardisation (e.g, pertaining to representation, realisation  of rules & norms). In these contexts, this highlight paper positions
 recent research from IJCAI 2019 aimed at advancing humancentred  AI principles in the backdrop of the autonomous driving  application domain. From a technical viewpoint, the highlighted research  provides a model for advancing the state of the art in reasoning
 about space and motion, combining reasoning and learning, nonmonotonic  reasoning, and computational modelling of high-level visuospatial  commonsense. In addition to demonstrating the significance  of integrated vision and semantics solutions in autonomous  driving, we also highlight open questions emphasising the need for  interdisciplinary mixed-methods research –involving AI, Psychology,  HCI– to better appreciate the complexity and spectrum of varied
 human-centred challenges in diverse naturalistic driving situations.

poster

ECAI2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI, including:




**An extensive programme of workshops, tutorials, and invited speakers**

**The Prestigious Applications of Intelligent Systems conference (PAIS)**

**The Frontiers in AI track sessions**

**The Lab To Market event**

**The Women in AI time**

**The EU Challenges forum**

… and many more!

ECAI 2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI.

The Winograd Schema Challenge (WSC) was proposed  by Levesque et al. in 2011 as a new test in Artificial Intelligence (AI)  and possibly as an alternative to the Turing test. WSC is a complex
 coreference resolution task which requires applying knowledge on  commonsense reasoning. It is an easy task for humans but it still remains  an unsolved challenge for computers. There are two categories  of proposed approaches for tackling the WSC. The first encompasses  techniques based on formalized Knowledge Representation and Reasoning  (KRR), while the second entails Machine Learning (ML)  approaches. In this paper we provide a review of the state-of-theart
 approaches proposed from both categories and we outline their  strengths and weaknesses. Additionally, we discuss a recent work  which combines techniques from both categories as it seems to be a  promising and innovative approach.

Review of the Recent Techniques for Learning Commonsense Knowledge applied to the Winograd Schema Challenge

This paper provides an overview of an architecture based on the principle of step-wise refinement for knowledge representation, explainable reasoning, and interactive learning, in robotics. We briefly describe the individual components of the architecture, and emphasize how the interplay between representation, reasoning, and learning, can be exploited to enable reliable and efficient decision making in dynamic domains

REBA-KRL: Refinement-based Architecture for Knowledge Representation, Explainable Reasoning, and Interactive Learning in Robotics

The problem of reasoning with context dependent knowledge has recently gained interest in the area of description logic based knowledge bases (KBs). Among the several proposals, we consider the Contextualized Knowledge Repository (CKR) framework. The CKR model has been recently extended with the capability of reasoning with global (context independent) defeasible axioms that can be overridden by local (context specific) knowledge. In CKR applications it is often useful to reason over a hierarchical organization of contexts. We highlight here our recent efforts on extending the CKR framework to allow for the representation of exception handling in the inheritance of knowledge across local contexts. We first concentrate on a limitation to a particular kind of context organization, i.e. ranked hierarchies, which allows us to simplify the definition of reasoning procedures.We then further generalize the proposal to extend the reasoning on exception handling over general contextual hierarchies.

Reasoning with Justifiable Exceptions in Contextual Hierarchies

Leo-III is an effective automated theorem prover for extensional type theory with Henkin semantics. It is based on an extensional higher-order paramodulation calculus and supports reasoning in monomorphic and rank-1 polymorphic first-order and higher-order logics. Leo-III also automates various non-classical logics, including almost every normal higher-order modal logic.

The Higher-Order Prover Leo-III

Actual Causality Canvas: A General Framework for Explanation-based Socio-Technical Constructs

Entropy-based adaptive exploit-explore coefficient for Monte-Carlo path planning

"Semantic interpretation of dynamic visuospatial imagery calls for a general and systematic integration of methods in knowledge representation and computer vision. Towards this, we highlight research articulating and developing deep (visuospatial) semantics, characterised by the existence of declarative models –e.g., pertaining space and motion– and corresponding formalisation and reasoning methods supporting capabilities such as semantic question-answering, relational visuospatial learning, and (non-monotonic) visuospatial explanation. We position a working model for deep semantics by highlighting our select recent works from IJCAI 2019, AAAI 2018, and ILP 2016 & ACS 2018. 

We posit that human-centred, explainable visual sensemaking necessitates both high-level semantics and low-level visual computing, with the highlighted works providing a model for systematic, modular integration of diverse multifaceted techniques and perspectives from AI, ML, Vision, Visual Perception, and Spatial Cognition."

Driven by Commonsense: On the Role of Human-Centred Visual Explainability for Autonomous Vehicles

Downloads

Next from ECAI 2020

Review of the Recent Techniques for Learning Commonsense Knowledge applied to the Winograd Schema Challenge

Similar lecture

Multimodal End-to-End Learning for Autonomous Steering in Adverse Road and Weather Conditions