Active cameras provide a navigating vehicle with the ability to fixate and track features over extended periods of time, and wide fields of view. While it is relatively straightforward to apply fixating vision to tactical, short-term navigation tasks, using serial fixation on a succession of features to provide global information for strategic navigation is more involved. However, active vision is seemingly well-suited to this task: the ability to measure features over such a wide range means that the same ones can be used as a robot makes a wide range of movements. This has advantages for map-building and localisation. The core work of this thesis concerns simultaneous localisation and map-building for a robot with a stereo active head, operating in an unknown environment and using point features in the world as visual landmarks. Importance has been attached to producing maps which are useful for extended periods of navigation. Many map-building methods fail on extended runs because ...

Previous work in simultaneous localisation and mapbuilding (SLAM) for mobile robots has focused on the simplified case in which a robot is considered to move in two dimensions on a ground plane. While this is sometimes a good approximation, a large number of real-world applications require robots to move around terrain which has significant slopes and undulations. In this paper we describe an EKFbased SLAM system permitting unconstrained 3D localisation, and in particular develop models for the motion of a wheeled robot in the presence of unknown slope variations. In a fully automatic implementation, our robot observes visual point features using fixating stereo vision and builds a sparse map on-the-fly. Combining this visual measurement with information from odometry and a roll/pitch accelerometer sensor, the robot performs accurate, repeatable localisation while traversing an undulating course. 1.

Abstract — This paper presents an integrated approach to exploration, mapping, and localization. Our algorithm uses a highly efficient Rao-Blackwellized particle filter to represent the posterior about maps and poses. It applies a decision-theoretic framework which simultaneously considers the uncertainty in the map and in the pose of the vehicle to evaluate potential actions. Thereby, it trades off the cost of executing an action with the expected information gain and takes into account possible sensor measurements gathered along the path taken by the robot. We furthermore describe how to utilize the properties of the Rao-Blackwellization to efficiently compute the expected information gain. We present experimental results obtained in the real world and in simulation to demonstrate the effectiveness of our approach. I.

. Active cameras provide a mobile robot with the capability to fixate and track features over a wide field of view. However, their use emphasises serial attention focussing on a succession of scene features, raising the question of how this should be best achieved to provide localisation information. This paper describes a fully automatic system, able to detect, store and track suitable landmark features during goal-directed navigation. The robot chooses which of the available set of landmarks to track at a certain time to best improve its position knowledge, and decides when it is time to search for new features. Localisation performance improves on that achieved using odometry alone and shows significant advantages over passive structure-from-motion techniques. Rigorous consideration is given to the propagation of uncertainty in the estimation of the positions of the robot and scene features as the robot moves, fixates and shifts fixation. The paper shows how the estimat...

... This paper develops active strategies for a robot to acquire visual experience through simple experimental manipulation. The experiments are oriented towards determining what parts of the environment are physically coherent -- that is, which parts will move together, and which are more or less independent. We argue that following causal chains of events out from the robot's body into the environment allows for a very natural developmental progression of visual competence, and relate this idea to results in neuroscience.

Acquiring the complete surface geometry of an object using a range scanner invariably requires that multiple range images be taken of it from different viewpoints. An algorithm is presented which solves the "next best view" (NBV) problem: determine the next position for the range scanner given its previous scans of the object. As part of a complete surface acquisition system the scanner's next position should cause it not only to sample more of the object's surface but to resample part of the object already scanned to allow for the registration and integration of the new data with the previous scans. A novel representation, positional space, is presented which facilitates a solution to the NBV problem by representing what must be and what can be scanned in a unified data structure. The expensive operation of determining the visibility of part of the viewing volume is computed only once, not for each potential position of the scanner, thus breaking the computational burden of choosing t...

We describe an automated scene modeling system that consists of two components operating in an interleaved fashion: an incremental modeler that builds solid models from range imagery, and a sensor planner that analyzes the resulting model and computes the next sensor position. This planning component is target-driven and computes sensor positions using model information about the imaged surfaces and the unexplored space in a scene. The method is shape-independent and uses a continuous-space representation that preserves the accuracy of sensed data. It is able to completely acquire a scene by repeatedly planning sensor positions, utilizing a partial model to determine volumes of visibility for contiguous areas of unexplored scene. These visibility volumes are combined with sensor placement constraints to compute sets of occlusion-free sensor positions that are guaranteed to improve the quality of the model. We show results for acquisition of a scene that includes multiple, distinct obje...

Ambiguity in scene information, due to noisy measurements and uncertain object models, can be quantified and actively used by an autonomous agent to efficiently gather new data and improve its information about the environment. In this work an information-based utility measure is used to derive from a learned classification of shape models an efficient data collection strategy, specifically aimed at increasing classification confidence when recognizing uncertain shapes. Promising experimental results are reported.

In this paper we introduce coverage maps as a new way of representing the environment of a mobile robot. Coverage maps store for each cell of a given grid a posterior about the amount the corresponding cell is covered by an obstacle. Using this representation a mobile robot can more accurately reason about its uncertainty in the map of the environment than with standard occupancy grids. We present a model for proximity sensors designed to update coverage maps upon sensory input. We also describe how coverage maps can be used to formulate a decision-theoretic approach for mobile robot exploration.

The paper deals with the registration and modeling of multiple 3-D profile maps acquired from different viewpoints by light striping. We analyze the propagation of measurement and calibration errors to the registration parameters and further to the reconstructed model of the scene consisting of planar patches. The analysis is performed for two strategies. In the first strategy, the maps are registered simultaneously using the Levenberg-Marquardt method to update the registration parameters and the model computed afterwards while in the second one, the maps are registered sequentially against the model reconstructed up till then using the method of unit quaternions to update the registration parameters. Our statistical analysis thus combines the registration and modeling steps, and in registration, we determine the corresponding points either on the parametric domains of the maps or as closest points in 3-D using the information from the parametric domain to restrict the search for the ...