Tomás Lozano-Pérez

An algorithm for planning collision-free paths among polyhedral obstacles

This paper describes a collision avoidance algorithm for planning a safe path for a polyhedral object moving among known polyhedral objects. The algorithm transforms the obstacles so that they represent the locus of forbidden positions for an arbitrary reference point on the moving object. A trajectory of this reference point which avoids all forbidden regions is free of collisions. Trajectories are found by searching a network which indicates, for each vertex in the transformed obstacles, which other vertices can be reached safely.

Solving the multiple instance problem with axis-parallel rectangles

The multiple instance problem arises in tasks where the training examples are ambiguous: a single example object may have many alternative feature vectors (instances) that describe it, and yet only one of those feature vectors may be responsible for the observed classification of the object. This paper describes and compares three kinds of algorithms that learn axis-parallel rectangles to solve the multiple instance problem. Algorithms that ignore the multiple instance problem perform very poorly. An algorithm that directly confronts the multiple instance problem (by attempting to identify which feature vectors are responsible for the observed classifications) performs best, giving 89% correct predictions on a musk odor prediction task. The paper also illustrates the use of artificial data to debug and compare these algorithms.

Automatic Synthesis of Fine-Motion Strategies for Robots

Active compliance enables robots to carry out tasks in the presence of significant sensing and control errors. Compliant motions are quite difficult for humans to specify, however. Furthermore, robot programs are quite sensitive to details of geometry and to error characteristics and must, therefore, be constructed anew for each task. These factors motivate the search for automatic synthesis tools for robot program ming, especially for compliant motion. This paper describes a formal approach to the synthesis of compliant-motion strategies from geometric descriptions of assembly operations and explicit estimates of errors in sensing and control. A key aspect of the approach is that it provides criteriafor correct ness of compliant-motion strategies.

Automatic Planning of Manipulator Transfer Movements

The class of problems that involve finding where to place or how to move a solid object in the presence of obstacles is discussed. The solution to this class of problems is essential to the automatic planning of manipulator transfer movements, i.e., the motions to grasp a part and place it at some destination. For example, planning transfer movements requires the ability to plan paths for the manipulator that avoid collisions with objects in the workspace and the ability to choose safe grasp points on objects. The approach to these problems described here is based on a method of computing an explicit representation of the manipulator configurations that would bring about a collision.

On multiple moving objects

This paper explores the motion-planning problem for multiple moving objects. The approach taken consists of assigning priorities to the objects, then planning motions one object at a time. For each moving object, the planner constructs a configuration space-time that represents the time-varying constraints imposed on the moving object by the other moving and stationary objects. The planner represents this space-time approximately, using two-dimensional slices. The space-time is then searched for a collision-free path. The paper demonstrates this approach in two domains. One domain consists of translating planar objects; the other domain consists of two-link planar articulated arms.

Localizing Overlapping Parts by Searching the Interpretation Tree

This paper discusses how local measurements of positions and surface normals may be used to identify and locate overlapping objects. The objects are modeled as polyhedra (or polygons) having up to six degrees of positional freedom relative to the sensors. The approach operates by examining all hypotheses about pairings between sensed data and object surfaces and efficiently discarding inconsistent ones by using local constraints on: distances between faces, angles between face normals, and angles (relative to the surface normals) of vectors between sensed points. The method described here is an extension of a method for recognition and localization of nonoverlapping parts previously described in [18] and [15].

A subdivision algorithm in configuration space for findpath with rotation

A recursive cellular representation for configuration space is presented along with an algorithm for searching that space for collision-free paths. The details of the algorithm are presented for polygonal obstacles and a moving object with two translational and one rotational degrees of freedom.

An automatic registration method for frameless stereotaxy, image guided surgery, and enhanced reality visualization

There is a need for frameless guidance systems to help surgeons plan the exact location for incisions, to define the margins of tumors, and to precisely identify locations of neighboring critical structures. The authors have developed an automatic technique for registering clinical data, such as segmented magnetic resonance imaging (MRI) or computed tomography (CT) reconstructions, with any view of the patient on the operating table. The authors demonstrate on the specific example of neurosurgery. The method enables a visual mix of live video of the patient and the segmented three-dimensional (3-D) MRI or CT model. This supports enhanced reality techniques for planning and guiding neurosurgical procedures and allows us to interactively view extracranial or intracranial structures nonintrusively. Extensions of the method include image guided biopsies, focused therapeutic procedures, and clinical studies involving change detection over time sequences of images.

A geometric modeling system for automated mechanical assembly

Very high level languages for describing mechanical assembly require a representation of the geometric and physical properties of 3-D objects including parts, tools, and the assembler itself. This paper describes a geometric modeling system that generates a data base in which objects and assemblies are represented by nodes in a graph structure. The edges of the graph represent relationships among objects such as part-of, attachment, constraint, and assembly. The nodes also store positional relationships between objects and physical properties such as material type. The user designs objects by combining positive and negative parameterized primitive volumes, for example, cubes and cones, which are represented internally as polyhedra. The data base is built by invoking a procedural representation of the primitive volumes, which generates vertex, edge, and surface lists of instances of the volumes. Several applications in the automatic assembly domain have been implemented using the geometric modeling system as a basis.

Image database retrieval with multiple-instance learning techniques

In this paper, we develop and test an approach for retrieving images from an image database based on content similarity. First, each picture is divided into many overlapping regions. For each region, the sub-picture is filtered and converted into a feature vector. In this way, each picture is represented by a number of different feature vectors. The user selects positive and negative image examples to train the system. During the training, a multiple-instance learning method known as the diverse density algorithm is employed to determine which feature vector in each image best represents the users concept, and which dimensions of the feature vectors are important. The system tries to retrieve images with similar feature vectors from the remainder of the database. A variation of the weighted correlation statistic is used to determine image similarity. The approach is tested on a medium-sized database of natural scenes as well as single- and multiple-object images.