Anyone who has read a number of bridge columns in newspapers will be struck by the frequency with which even the world's top players make mistakes. . . .The key . . . lies in writing a program that can play the cards "perfectly."
– David Levy, from The Million Pound Bridge Program. In Heuristic Programming in Artificial Intelligence: The Second Computer Olympiad. Ellis Horwood Series in Artificial Intelligence. March, 1991.
EIT Digital is putting its weight behind the concept of autonomous robot colleagues for hard-pressed professionals in elderly care provision by supporting the development of SARA (Social & Autonomous Robotic health Assistant) as part of its focus on Digital Wellbeing. SARA is a consortium-led initiative that aims to improve the quality of care in nursing homes and hospitals by introducing robots as social entities – taking on time-consuming tasks and interacting with patients without requiring a human operator. The consortium includes analytics and data science specialist Bright Cape, Forum Virium Helsinki, GIM Robotics, Curamatik and TU Berlin. The idea is to address the twin challenges of caring for a rapidly ageing population and an acute shortage of healthcare professionals, helping to balance a workload that is under ever-increasing pressure: it is estimated that 13.8% of nurses deal every week with the consequences of heavy work pressure – medication errors, for example – while patients feel the impact on quality of care. While there is nothing new about the idea of robot colleagues in healthcare, most of the current generation of robots perform activities that need to be set up and led by a human operator.
Commercial 3-D printing--or additive manufacturing (AM)--is a booming industry. But if printers were liberated from the typical setup involving an immobile box and a gantry, and set free to work in roving, collaborative teams, the AM business might be much bigger with many more applications, including as robotic masons at construction sites and repairing crumbling urban and rural civil infrastructure. A multidisciplinary robotics team at the NYU Tandon School of Engineering, hosted by NYU's Center for Urban Science and Progress (CUSP) and supported by a $1.2 million grant from the National Science Foundation (NSF), is working to make the concept a reality by designing autonomous systems for 3-D printers on robotic arms attached to mobile, roving platforms. Functioning in teams--a concept called collective additive manufacturing (CAM)--these printers, with machine learning and other artificial intelligence (AI) capabilities, could repair bridges, tunnels and other civic structures; work in ocean depths and disaster zones; or even head to space to work on the Moon, Mars, and beyond. Feng explained that the goal is for accuracy, efficiency, and adaptability to the environment and to real-time conditions--rather the way a navigation app reroutes a vehicle that it senses has veered from a mapped course.
A computer program that uses AI planning techniques is now the world champion computer program in the game of Contract Bridge. As reported in The New York Times and The Washington Post, this program--a new version of Great Game Products' The classical approach used in AI programs for games of strategy is to do a game tree search using the well-known minimax formula (eq. 1) The minimax computation is basically a bruteforce search: If implemented as formulated here, it would examine every node in the game tree. In practical implementations of minimax game tree searching, a number of techniques are used to improve the efficiency of this computation: putting a bound on the depth of the search, using alpha-beta pruning, doing transposition-table lookup, and so on. However, even with enhancements such as these, minimax computations often involve examining huge numbers of nodes in the game tree. Because a Bridge hand is typically played in just a few minutes, there is not enough time for a game tree search to search enough of this tree to make good decisions.
Robot bridge inspector uses sensors and machine learning to hunt for defects Researchers at the University of Nevada have developed an autonomous robot, designed to inspect bridges and detect any structural damage before it can cause potential injury. The four-wheeled robot bridge inspector, called Seekur, uses a variety of tools to carry out its important task. Researchers at the University of Nevada have developed an autonomous robot, designed to inspect bridges and detect any structural damage before it can cause potential injury. The four-wheeled robot bridge inspector, called Seekur, uses a variety of tools to carry out its important task.
Autonomous bridge-inspecting robot could save lives by using smart sensors and machine learning algorithms to detect dangerous defects. Researchers at the University of Nevada have developed an autonomous robot, designed to inspect bridges and detect any structural damage before it can cause potential injury. The four-wheeled robot bridge inspector, called Seekur, uses a variety of tools to carry out its important task. These include ground-penetrating radar for looking beneath the surface of a bridge for underlying instabilities, sensors designed to search for possible corrosion of steel or cement, and a camera which analyzes cracks in the bridge's surface. A machine learning algorithm then analyzes all of this information and uses it to generate a color-coded map, which is passed on to (human) engineers to make them aware of weak spots.
Bridge Baron is a computer program that plays bridge. It won the 1997 world championship of computer bridge, the Baron Barclay World Bridge Computer Challenge, as reported in The New York Times and The Washington Post. The five-day competition, which was hosted by the American Contract Bridge League in July 1997, included five computer programs, from the US, Japan, and Germany. The Bridge Baron won every head-to-head match that it played against the other programs.
Contract bridge is an example of an incomplete information game for which computers typically do not perform better than expert human bridge players. In particular, the typical bidding decisions of human bridge players are difficult to mimic with a computer program, and thus automatic bridge bidding remains to be a challenging research problem. Currently, the possibility of automatic bidding without mimicking human players has not been fully studied. In this work, we take an initiative to study such a possibility for the specific problem of bidding without competition. We propose a novel learning framework to let a computer program learn its own bidding decisions. The framework transforms the bidding problem into a learning problem, and then solves the problem with a carefully designed model that consists of cost-sensitive classifiers and upper-confidence-bound algorithms. We validate the proposed model and find that it performs competitively to the champion computer bridge program that mimics human bidding decisions.
This paper investigates the problems arising in the construction of a program to play the game of contract bridge. These problems include both the difficulty of solving the game's perfect information variant, and techniques needed to address the fact that bridge is not, in fact, a perfect information game. GIB, the program being described, involves five separate technical advances: partition search, the practical application of Monte Carlo techniques to realistic problems, a focus on achievable sets to solve problems inherent in the Monte Carlo approach, an extension of alpha-beta pruning from total orders to arbitrary distributive lattices, and the use of squeaky wheel optimization to find approximately optimal solutions to cardplay problems. GIB is currently believed to be of approximately expert caliber, and is currently the strongest computer bridge program in the world.
Although game-tree search works well in perfectinformation games, there are problems in trying to use it for imperfect-information games such as bridge. The lack of knowledge about the opponents' possible moves gives the game tree a very large branching factor, making the ree so immense that game-tree searching is infeasible. In this paper, we describe our approach for overcoming this problem. We develop a model of imperfect-information games, and describe how to represent information about the game using a modified version of a task network that is extended to represent multi-agency and uncertainty. We present a game-playing procedure that uses this approach to generate game trees in which the set of alternative choices is determined not by the set of possible actions, but by the set of available tactical and strategic schemes.
AI planning techniques are beginning to find use in a number of practical planning domains. However, the backward-chaining and partial-order-planning control strategies traditionally used in AI planning systems are not necessarily the best ones to use for practical planning problems. In this paper, we discuss some of the difficulties that can result from the use of backward chaining and partial-order planning, and we describe how these difficulties can be overcome by adapting Hierarchical Task-Network (HTN) planning to use a total-order control strategy that generates the steps of a plan in the same order that those steps will be executed. We also examine how introducing the total-order restriction into HTN planning affects its expressive power, and propose a way to relax the total-order restriction to increase its expressive power and range of applicability.