This paper describes an architecture for robots that combines the complementary strengths of probabilistic graphical models and declarative programming to represent and reason with logic-based and probabilistic descriptions of uncertainty and domain knowledge. An action language is extended to support non-boolean fluents and nondeterministic causal laws. This action language is used to describe tightly-coupled transition diagrams at two levels of granularity, with a fine-resolution transition diagram defined as a refinement of a coarse-resolution transition diagram of the domain. The coarse-resolution system description, and a history that includes (prioritized) defaults, are translated into an Answer Set Prolog (ASP) program. For any given goal, inference in the ASP program provides a plan of abstract actions. To implement each such abstract action, the robot automatically zooms to the part of the fine-resolution transition diagram relevant to this action. A probabilistic representation of the uncertainty in sensing and actuation is then included in this zoomed fine-resolution system description, and used to construct a partially observable Markov decision process (POMDP). The policy obtained by solving the POMDP is invoked repeatedly to implement the abstract action as a sequence of concrete actions, with the corresponding observations being recorded in the coarse-resolution history and used for subsequent reasoning. The architecture is evaluated in simulation and on a mobile robot moving objects in an indoor domain, to show that it supports reasoning with violation of defaults, noisy observations and unreliable actions, in complex domains. 1 We use the terms "robot" and "agent" interchangeably in this paper. 1 arXiv:1508.03891v4 [cs.RO] 21 Sep 2018 probability reason optimally (or near optimally) about the effects of numerically quantifiable uncertainty in sensing and action. There have been many attempts to combine the benefits of these two classes of systems, including work on joint (i.e., logic-based and probabilistic) representations of state and action, and algorithms for planning and decisionmaking in such formalisms. These approaches provide significant expressive power, but they also impose a significant computational burden. More efficient (and often approximate) reasoning algorithms for such unified probabilisticlogical paradigms are being developed. However, practical robot systems that combine abstract task-level planning with probabilistic reasoning, link, rather than unify, their logic-based and probabilistic representations, primarily because roboticists often need to trade expressivity or correctness guarantees for computational speed. Information close to the sensorimotor level is often represented probabilistically to quantitatively model and reason about the uncertainty in sensing and actuation, with the robot's beliefs including statements such as "the robotics book is on the shelf with probability 0.9". At the same time, logic-based systems are used to reason with (more) abstract commonsen...

Deployment of robots in practical domains poses key knowledge representation and reasoning challenges. Robots need to represent and reason with incomplete domain knowledge, acquiring and using sensor inputs based on need and availability. This paper presents an architecture that exploits the complementary strengths of declarative programming and probabilistic graphical models as a step toward addressing these challenges. Answer Set Prolog (ASP), a declarative language, is used to represent, and perform inference with, incomplete domain knowledge, including default information that holds in all but a few exceptional situations. A hierarchy of partially observable Markov decision processes (POMDPs) probabilistically models the uncertainty in sensor input processing and navigation. Nonmonotonic logical inference in ASP is used to generate a multinomial prior for probabilistic state estimation with the hierarchy of POMDPs. It is also used with historical data to construct a beta (meta) density model of priors for metareasoning and early termination of trials when appropriate. Robots equipped with this architecture automatically tailor sensor input processing and navigation to tasks at hand, revising existing knowledge using information extracted from sensor inputs. The architecture is empirically evaluated in simulation and on a mobile robot visually localizing objects in indoor domains.

Algorithms based on deep network models are being used for many pattern recognition and decision-making tasks in robotics and AI. Training these models requires a large labeled dataset and considerable computational resources, which are not readily available in many domains. Also, it is difficult to understand the internal representations and reasoning mechanisms of these models. The architecture described in this paper attempts to address these limitations by drawing inspiration from research in cognitive systems. It uses non-monotonic logical reasoning with incomplete commonsense domain knowledge, and inductive learning of previously unknown constraints on the domain's states, to guide the construction of deep network models based on a small number of relevant training examples. As a motivating example, we consider a robot reasoning about the stability and partial occlusion of configurations of objects in simulated images. Experimental results indicate that in comparison with an architecture based just on deep networks, our architecture improves reliability, and reduces the sample complexity and time complexity of training deep networks.• Attempts to perform the estimation tasks based on nonmonotonic logical reasoning with incomplete commonsense domain knowledge and the extracted geometric relationships between scene objects. • Uses the labeled examples, i.e., images with occlusion labels for objects and stability labels for object struc-

No abstract

Abstract-Mobile robot localization, the ability of a robot to determine its global position and orientation, continues to be a major research focus in robotics. In most past cases, such localization has been studied on wheeled robots with rangefinding sensors such as sonar or lasers. In this paper, we consider the more challenging scenario of a legged robot localizing with a limited field-of-view camera as its primary sensory input. We begin with a baseline implementation adapted from the literature that provides a reasonable level of competence, but that exhibits some weaknesses in real-world tests. We propose a series of practical enhancements designed to improve the robot's sensory and actuator models that enable our robots to achieve a 50% improvement in localization accuracy over the baseline implementation. We go on to demonstrate how the accuracy improvement is even more dramatic when the robot is subjected to large unmodeled movements. These enhancements are each individually straightforward, but together they provide a roadmap for avoiding potential pitfalls when implementing Monte Carlo Localization on vision-based and/or legged robots.

This paper describes an architecture that combines the complementary strengths of declarative programming and probabilistic graphical models to enable robots to represent, reason with, and learn from, qualitative and quantitative descriptions of uncertainty and knowledge. An action language is used for the low-level (LL) and high-level (HL) system descriptions in the architecture, and the definition of recorded histories in the HL is expanded to allow prioritized defaults. For any given goal, tentative plans created in the HL using default knowledge and commonsense reasoning are implemented in the LL using probabilistic algorithms, with the corresponding observations used to update the HL history. Tight coupling between the two levels enables automatic selection of relevant variables and generation of suitable action policies in the LL for each HL action, and supports reasoning with violation of defaults, noisy observations and unreliable actions in large and complex domains. The architecture is evaluated in simulation and on physical robots transporting objects in indoor domains; the benefit on robots is a reduction in task execution time of 39% compared with a purely probabilistic, but still hierarchical, approach.

No abstract

A central goal of robotics and AI is to be able to deploy an agent to act autonomously in the real world over an extended period of time. To operate in the real world, autonomous robots rely on sensory information. Despite the potential richness of visual information from on-board cameras, many mobile robots continue to rely on non-visual sensors such as tactile sensors, sonar, and laser. This preference for relatively low-fidelity sensors can be attributed to, among other things, the characteristic requirement of realtime operation under limited computational resources. Illumination changes pose another big challenge. For true extended autonomy, an agent must be able to recognize for itself when to abandon its current model in favor of learning a new one; and how to learn in its current situation. We describe a self-contained vision system that works on-board a vision-based autonomous robot under varying illumination conditions. First, we present a baseline system capable of color segmentation and object recognition within the computational and memory constraints of the robot. This relies on manually labeled data and operates under constant and reasonably uniform illumination conditions. We then relax these limitations by introducing algorithms for (i) Autonomous planned color learning, where the robot uses the knowledge of its environment (position, size and shape of objects) to automatically generate a suitable motion sequence and learn the desired colors, and (ii) Illumination change detection and adaptation, where the robot recognizes for itself when the illumination conditions have changed sufficiently to warrant revising its knowledge of colors. Our al-M. Sridharan ( ) · P. Stone gorithms are fully implemented and tested on the Sony ERS-7 Aibo robots.