Learning Task Knowledge and its Scope of Applicability in Experience-Based Planning Domains

arXiv.org Artificial Intelligence

Experience-based planning domains (EBPDs) have been recently proposed to improve problem solving by learning from experience. EBPDs provide important concepts for long-term learning and planning in robotics. They rely on acquiring and using task knowledge, i.e., activity schemata, for generating concrete solutions to problem instances in a class of tasks. Using Three-Valued Logic Analysis (TVLA), we extend previous work to generate a set of conditions as the scope of applicability for an activity schema. The inferred scope is a bounded representation of a set of problems of potentially unbounded size, in the form of a 3-valued logical structure, which allows an EBPD system to automatically find an applicable activity schema for solving task problems. We demonstrate the utility of our approach in a set of classes of problems in a simulated domain and a class of real world tasks in a fully physically simulated PR2 robot in Gazebo.


I know there's a lot on your plate this year, so don't worry about all these robots we're making

Mashable

Okay, so you've probably seen an influx of robots and robot stories getting shared on the internet lately, and you've probably experienced some anxiety about some sort of impending robot-related doom.


Could robots be counselors? Early research shows positive user experience: New research has shown for the first time that a social robot can deliver a 'helpful' and 'enjoyable' motivational interview

#artificialintelligence

Many participants in the University of Plymouth study praised the'non-judgemental' nature of the humanoid NAO robot as it delivered its session -- with one even saying they preferred it to a human. Led by the School of Psychology, the study also showed that the robot achieved a fundamental objective of MI as it encouraged participants, who wanted to increase their physical activity, to articulate their goals and dilemmas aloud. MI is a technique that involves the counsellor supporting and encouraging someone to talk about their need for change, and their reasons for wanting to change. The role of the interviewer in MI is mainly to evoke a conversation about change and commitment, and the robot was programmed with a set script designed to elicit ideas and conversation on how someone could increase their physical activity. When finished answering each question, the participant taped the top of NAO's head to continue, with some sessions lasting up to an hour.


No systematic cover-up of Iraq troop activity logs: Defense Ministry

The Japan Times

The Defense Ministry said Wednesday its probe had found no organizational cover-up of troop activity logs related to a controversial deployment to war-torn Iraq between 2004 and 2006. The ministry initially claimed that the logs had been discarded in response to a request for their disclosure by an opposition lawmaker in February 2017. However the logs were discovered later that year, prompting the ministry to investigate. Based on the findings, the ministry reprimanded a total of 17 people, including Vice Defense Minister Katashi Toyota, who was held responsible for the logs' insufficient supervision. It was not until March this year that Defense Minister Itsunori Onodera learned that the activity logs still existed, a year after their discovery.


Activity Net

@machinelearnbot

Our benchmark aims at covering a wide range of complex human activities that are of interest to people in their daily living. We illustrate three scenarios in which ActivityNet can be used to compare algorithms for human activity understanding: global video classification,trimmed activity classification and activity detection.