This paper describes an implementation of the 3T robot architecture which has been under development for the last eightyears. The architecture uses three levels of abstraction and description languages whichare compatible between levels. The makeup of the architecture helps to coordinate planful activities with real-time behaviors for dealing with dynamic environments. In recent years, other architectures have been created with similar attributes but two features distinguish the 3T architecture: 1) a variety of useful software tools have been created to help implement this architecture on multiple real robots;, and 2) this architecture, or parts of it, have been implemented on a varietyofvery different robot systems using different processors, operating systems, effectors and sensor suites.

The Spatial Semantic Hierarchy is a model of knowledge of large-scale space consisting of multiple interacting representations, both qualitative and quantitative. The SSH is inspired by the properties of the human cognitive map, and is intended to serve both as a model of the human cognitive map and as a method for robot exploration and map-building. The multiple levels of the SSH express states of partial knowledge, and thus enable the human or robotic agent to deal robustly with uncertainty during both learning and problem-solving. The control level represents useful patterns of sensorimotor interaction with the world in the form of trajectory-following and hill-climbing control laws leading to locally distinctive states. Local geometric maps in local frames of reference can be constructed at the control level to serve as observers for control laws in particular neighborhoods. The causal level abstracts continuous behavior among distinctive states into a discrete model ...

. Research in Qualitative Reasoning builds and uses discrete symbolic models of the continuous world. Inference methods such as qualitative simulation are grounded in the theory of ordinary differential equations. We argue here that cognitive mapping --- building and using symbolic models of the large-scale spatial environment --- is a highly appropriate domain for qualitative reasoning research. We describe the Spatial Semantic Hierarchy (SSH), a set of distinct representations for space, each with its own ontology, each with its own mathematical foundation, and each abstracted from the levels below it. At the control level, the robot and its environment are modeled as a continuous dynamical system, whose stable equilibrium points are abstracted to a discrete set of "distinctive states." Trajectories linking these states can be abstracted to actions, giving a discrete causal graph level of representation for the state space. Depending on the properties of the actions, th...

We present a complete architecture for behavioral control of locomotion for both real and simulated agents and provide a design methodology for building the locomotion control systems that embody the architecture. A low-level locomotion engine controls an agent's actions directly based on intermediate-level reactive behaviors such as attraction and avoidance. High-level state machines schedule and control the reactive behaviors allowing for more "intelligent" decision processes, and an agent model provides a mechanism for varying locomotion according to agent state and personality attributes. In addition to providing specifications for a locomotion engine, we address the problem of selecting and organizing an appropriate set of behaviors. We present selection criteria and a method for partitioning the behaviors to aid in implementation. We discuss the challenges specific to human locomotion and explain how to...

This paper describes an implementation of the 3 T robot architecture which has been under development for the last eightyears. The architecture uses three levels of abstraction and description languages whichare compatible between levels. The makeup of the architecture helps to coordinate planful activities with real-time behaviors for dealing with dynamic environments. In recentyears, other architectures have been created with similar attributes but two features distinguish the 3 Tarchitecture: 1) a variety of useful software tools have been created to help implement this architecture on multiple real robots# and 2) this architecture, or parts of it, have been implemented on a varietyofvery different robot systems using different processors, operating systems, effectors and sensor suites.

. This paper proposes a hybrid robotic system for autonomous navigation in a complex and totally or partially unknown environment. The system is capable of handling real-world and real-time scenarios, integrating different paradigms of representation: symbolic, diagrammatic, procedural. In this sense it is `hybrid'. The paper presents the cognitive model, focusing on the perceptive processes. It describes a suitable analogical representation for the environment in which the robot operates together with the techniques used for the integration of sensor data and their fusion with a priori information. A concurrent operating system has also been developed to co-ordinate the different processes : perceptive, reactive, internal, etc. Its architecture reflects the cognitive model used, allowing the processes to be distributed both on the robot and on a remote workstation. 1. INTRODUCTION This paper proposes a hybrid robotic system for autonomous navigation in a complex and totall...

Navigation Templates (NaTs) provid amethod for constructing highly flexible navigation plans which capture the essence of the navigation situation (i.e., the taskand relevant environmental constraints). This paper presents NaTs asapplied to ad]q]ImxIB2 simulator of NASA's Personal Satellite Assistant the PSA. The specifics of this applicationrequired that the basic NaT algorithm be supplemented with certain memoryadorym-/ inordI to function reliably with the narrow beam range sensors with which the PSA simulator isequipped These modem-B'q[mx and the results are presented Keywords: Na igation templates, na igation plan, robot na igation 1. Background The PSA is a new intra- ehicular robot dbot m-I by NASA for use insid- the International Space Station. Each PSA will be equipped with a camera, dmera, microphone , speakers and a full micro-gra ity mobility system. The PSAs will be used to keep track of object/personnel whereabouts in the station, teleconferencing and monitoring of experiments [1,2]. Because the Space Station is a dmq]I[q en ironment, the PSA need2 to be able to find its way from location to location e en when objects are mo ed contrary to its internal map e en when objects are mo ing through the same space at the same time in the area it is trying to tra erse. PSAs must ne er run into an astronaut, and should make e ery possible effort to get out of the astronaut's way.

This paper presents a method for assessing the distancebetween a mobile robot and an obstacle. The idea is to make use of stereocameras that are mountedona pan-tilt platform (the pan-tilt device itself is mounted on a mobile robot). When an obstacle occurs, the pantilt device drives the stereocameras to an orientation such that the left and right images of the obstacle are in a symmetrical position with respect to the vertical central line of the horizontally aligned stereo images. In this configuration, the distance between the left and right images of the obstacle is a function of the depth between the mobile robot and the obstacle. We qualitatively establish this relationship by using a look-up-table or 2D graph to avoid the need of doing 3D reconstruction. Therefore, no calibration is needed to determine the intrinsic/extrinsic parameters of the stereo-vision.

has demonstrated the important benefits that mobility adds to planetary exploration. Very soon, mission requirements will impose that planetary exploration rovers drive over-the-horizon in a single command cycle. This will require an evolution of the methods and technologies currently used. This paper presents experimental validation of our over-the-horizon autonomous planetary navigation. We present our approach to 3D terrain reconstruction from large sparse range data sets, localization and autonomous navigation in a Mars-like terrain. Our approach is based on on-line acquisition of range scans, map construction from these scans, path planning and navigation using the map. An Autonomy Engine supervises the whole process ensuring the safe navigation of the planetary rover. The outdoor experimental results demonstrate the effectiveness of the reconstructed terrain model for rover localization, path planning and motion execution scenario as well as the autonomy capability of our approach. I.

Control has to do with the intelligent, adaptive execution of a piece of a task, or an action, and with its interaction with the environment; at the same time, it copes with the disturbances coming from the external world (i.e., with the “struggle of the world” against our intentions). Planning has to do with the definition of sequences of actions, or tasks, to attain complex goals. The relation between planning and control is traditionally considered hierarchical: planning is performed at a higher level of abstraction as compared with control. Artificial intelligence (AI) planning systems are calculi that operate on explicit, declarative representations of both actions and states of the world. Their primitive terms denote actions, constraints, events, situations, scheduling relations, temporal entities and their relations, and so on. Paradigmatic of this approach is traditional, symbolic AI, according to which planning consists of a specific form of logical inference. Similar in this respect are other approaches to planning based on forms of representation such as graphs, Bayesian networks, Petri nets, and so on (see [1] for a review). In most cases, however, planning and control run concurrently, influencing each other on the same time scale. As a consequence, the problem arises of devising models of reasoning and kinds of representations that