A key step towards achieving human-level intelligence is to endow computers with reasoning abilities common to most people but absent from the current best artificial intelligence systems. Tests of intelligence can play an important role in this endeavour. We suggest some criteria for tests that measure progress towards human-level artificial intelligence (HLAI) and argue that tasks designed to study child cognition can be used in constructing such tests. When these tasks are presented in properly constructed simulated environments, which we call microcosms, systems that test well will represent significant progress towards achieving broad HLAI. We illustrate this approach using the domain of infant physical reasoning.

Many problems in AI, including planning, logical reasoning and probabilistic inference, have been shown to reduce to (weighted) constraint satisfaction. While there are a number of approaches for solving such problems, the recent gains in efficiency of the satisfiability approach have made SAT solvers a popular choice. Modern propositional SAT solvers are efficient for a wide variety of problems. However, particularly in the case of spatial reasoning, conversion to propositional SAT can sometimes result in a large number of variables and/or clauses. Moreover, spatial reasoning problems can often be more efficiently solved if the agent is able to exploit the geometric nature of space to make better choices during search and backtracking. The result of these two drawbacks — larger problem sizes and inefficient search — is that even simple spatial constraint problems are often intractable in the SAT approach. In this paper we propose a spatial reasoning system that provides significant performance improvements in constraint satisfaction problems involving spatial predicates. The key to our approach is to integrate a diagrammatic representation with a DPLL-based backtracking algorithm that is specialized for spatial reasoning. The resulting integrated system can be applied to larger and more complex problems than current approaches and can be adopted to improve performance in a variety of problems ranging from planning to probabilistic inference

We describe a cognitive architecture for creating more robust intelligent systems. Our approach is to enable hybrids of algorithms based on different computational formalisms to be executed. The architecture is motivated by some features of human cognitive architecture and the following beliefs: 1) Most existing computational methods often exhibit some of the characteristics desired of intelligent systems at the cost of other desired characteristics and 2) a system exhibiting robust intelligence can be designed by implementing hybrids of these computational methods. The main obstacle to this approach is that the various relevant computational methods are based on data structures and algorithms that are difficult to integrate into one system. We describe a new method of executing hybrids of algorithms using the focus of attention of multiple modules. The key to this approach is the following two principles: 1) Algorithms based on very different computational frameworks (e.g., logical reasoning, probabilistic inference, and case-based reasoning) can be implemented using the same set of five common functions and 2) each of these common functions can be executed using multiple data structures and algorithms. This approach has been embodied in the Polyscheme cognitive architecture. Systems based on Polyscheme in planning, spatial reasoning, robotics, and information retrieval illustrate that this approach to hybridizing algorithms enables qualitative and measurable quantitative advances in the abilities of intelligent systems.

How do children learn how to play hide and seek? At age 3-4, children do not typically have perspective taking ability, so their hiding ability should be extremely limited. We show through a case study that a 3 1/2 year old child can, in fact, play a credible game of hide and seek, even though she does not seem to have perspective taking ability. We propose that children are able to learn how to play hide and seek by learning the features and relations of objects (e.g., containment, under) and use that information to play a credible game of hide and seek. We model this hypothesis within the ACT-R cognitive architecture and put the model on a robot, which is able to mimic the child's hiding behavior. We also take the "hiding" model and use it as the basis for a "seeking" model. We suggest that using the same representations and procedures that a person uses allows better interaction between the human and robotic system.

We propose that an important aspect of human-robot interaction is perspective-taking. We show how perspective-taking occurs in a naturalistic environment (astronauts working on a collaborative project) and present a cognitive architecture for performing perspective-taking called Polyscheme. Finally, we show a fully integrated system that instantiates our theoretical framework within a working robot system. Our system successfully solves a series of perspective-taking problems and uses the same frames of references that astronauts do to facilitate collaborative problem solving with a person.