Developing autonomous decision-making requires safety assurance. Agent programming languages like AgentSpeak and Gwendolen provide tools for programming autonomous decision-making. However, despite numerous efforts to apply model checking to these languages, challenges persist such as a faithful semantic mapping between agent programs and the generated models, efficient model generation, and efficient model checking. As an extension of the agent programming language GOAL, vGOAL has been proposed to formally specify autonomous decisions with an emphasis on safety. This paper tackles the mentioned challenges through two automated model-checking processes for vGOAL: one for Computation Tree Logic and another for Probabilistic Computation Tree Logic. Compared with the existing model-checking approaches of agent programming languages, it has three main advantages. First, it efficiently performs automated model-checking analysis for a given vGOAL specification, including efficiently generating input models for NuSMV and Storm and leveraging these efficient model checkers. Second, the semantic equivalence is established for both nondeterministic models and probabilistic models of vGOAL: from vGOAL to transition systems or DTMCs. Third, an algorithm is proposed for efficiently detecting errors, which is particularly useful for vGOAL specifications that describe complex scenarios. Validation and experiments in a real-world autonomous logistic system with three autonomous mobile robots illustrate both the efficiency and practical usability of the automated CTL and PCTL model-checking process for vGOAL.

The Robot Operating System (ROS) is a widely used framework for building robotic systems. It offers a wide variety of reusable packages and a pattern for new developments. It is up to developers how to combine these elements and integrate them with decision-making for autonomous behavior. The feature of such decision-making that is in general valued the most is safety assurance. In this research preview, we present a formal approach for generating safe autonomous decision-making in ROS. We first describe how to improve our existing static verification approach to verify multi-goal multi-agent decision-making. After that, we describe how to transition from the improved static verification approach to the proposed runtime verification approach. An initial implementation of this research proposal yields promising results.

The combination of analytics, automation and augmented intelligence will drive the future of business. That was the message delivered by Ray Wang, founder and analyst at Constellation Research, who spoke recently during the Graph AI Summit, the spring edition of the biannual open conference hosted virtually by graph data and analytics vendor TigerGraph. According to Wang, nearly two-thirds of the companies that made up the Fortune 500 in 2000 are now gone, having been acquired, merged with another company or gone bankrupt. And by 2040, 80% will have disappeared. Meanwhile, tech vendors such as Amazon, Apple, Facebook and Microsoft have quintupled their market capitalization in the last five years alone.

"I think we're the first company [in this space] to really have a vision about autonomous decision-making, which means no human in the loop," Saarenvirta said. "Our vision is to help insurance companies autonomously detect fraud and automate claims as much as possible…. We want to be the market leader in bringing autonomous decision-making to insurance around fraud detection, claims automation - as well as underwriting, which is something we're looking to get into as well." The phrase autonomous is often used too liberally. It is generally the case that when companies refer to'AI' what they really mean is predictive analytics, which is just statistical analysis.

Today the UK natural intelligence company Opteran has raised around €2.3 million in seed funding to pioneer its lightweight, silicon-based approach to autonomy, created by testing insect brains, in what to some would sound a little like a Black Mirror episode. Opteran is a University of Sheffield spin-out based on eight years of research by Professor James Marshall and Dr. Alex Cope into insect brains as part of the Green Brain and Brains on Board projects. Although insects have smaller brains, they are still capable of sophisticated decision making and navigation using optic flow to perceive depth and distance. The Opteran team state that this is a far more efficient, robust and transparent way to achieve autonomy than current deep learning techniques, enabling the team to reverse-engineer insect brains to produce algorithms requiring no data centre or extensive pre-training. It means Opteran can mimic tasks such as seeing, sensing objects, obstacle avoidance, navigation and decision making.

We study the design of learning architectures for behavioural planning in a dense traffic setting. Such architectures should deal with a varying number of nearby vehicles, be invariant to the ordering chosen to describe them, while staying accurate and compact. We observe that the two most popular representations in the literature do not fit these criteria, and perform badly on an complex negotiation task. We propose an attention-based architecture that satisfies all these properties and explicitly accounts for the existing interactions between the traffic participants. We show that this architecture leads to significant performance gains, and is able to capture interactions patterns that can be visualised and qualitatively interpreted. Videos and code are available at https://eleurent.github.io/social-attention/.

As autonomous systems are becoming more and more pervasive, they often have to make decisions concerning moral and ethical values. There are many approaches to incorporating moral values in autonomous decision-making that are based on some sort of logical deduction. However, we argue here, in order for decision-making to seem persuasive to humans, it needs to reflect human values and judgments. Employing some insights from our ongoing researchusing features of the blackboard architecture for a context-aware recommender system, and a legal decision-making system that incorporates supra-legal aspects, we aim to explore if this architecture can also be adapted to implement a moral decision-making system that generates rationales that are persuasive to humans. Our vision is that such a system can be used as an advisory system to consider a situation from different moral perspectives, and generate ethical pros and cons of taking a particular course of action in a given context.