We show how map learning can be formulated as inference in a graphical model, which allows us to handle changing environments in a natural manner. We describe several different approximation schemes for the problem, and illustrate some results on a simulated grid-world with doors that can open and close. We close by briefly discussing how to learn more general models of (partially observed) environments, which can contain a variable number of objects with changing internal state. 1 Introduction Mobile robots need to navigate in dynamic environments: on a short time scale, obstacles, such as people, can appear and disappear, and on longer time scales, structural changes, such as doors opening and closing, can occur. In this paper, we consider how to create models of dynamic environments. In particular, we are interested in modeling the location of objects, which we can represent using a map. This enables the robot to perform path planning, etc. We propose a Bayesian approach in ...

Hidden Markov models (hmms) and partially observable Markov decision processes (pomdps) provide a useful tool for modeling dynamical systems. They are particularly useful for representing environments such as road networks and office buildings, which are typical for robot navigation and planning. The work presented here describes a formal framework for incorporating readily available odometric information into both the models and the algorithm that learns them. By taking advantage of such information, learning hmms/pomdps can be made better and require fewer iterations, while being robust in the face of data reduction. That is, the performance of our algorithm does not significantly deteriorate as the training sequences provided to it become significantly shorter. Formal proofs for the convergence of the algorithm to a local maximum of the likelihood function are provided. Experimental results, obtained from both simulated and real robot data, demonstrate the effectiveness of the approach....

We present a new method for training deformable models. Assume that we have training images where part locations have been labeled. Typically, one fits a model by maximizing the likelihood of the part labels. Alternatively, one could fit a model such that, when the model is run on the training images, it finds the parts. We do this by maximizing the conditional likelihood of the training data. We formulate model-learning as parameter estimation in a conditional random field (CRF). Initializing parameters with their maximum likelihood estimates, we reach the global optimum by gradient ascent. We present a learning algorithm that searches exhaustively over all part locations in an image without relying on feature detectors. This provides millions of examples of training data, and seems to avoid over-fitting issues known with CRFs. Results for part localization are relatively scarce in the community. We present results on three established datasets; Caltech motorbikes [8], USC people [19], and Weizmann horses [3]. In the Caltech set we significantly outperform the state-of-the-art [6]. For the challenging people dataset, we present results that are comparable to [19], but are obtained using a significantly more generic model (devoid of a face or skin detector). Our model is general enough to find other articulated objects; we use it to recover poses of horses in the challenging Weizmann database. 1.

Hidden Markov models (hmms) and partially observable Markov decision processes (pomdps) provide useful tools for modeling dynamical systems. They are particularly useful for representing the topology of environments such as road networks and office buildings, which are typical for robot navigation and planning. The work presented here describes a formal framework for incorporating readily available odometric information and geometrical constraints into both the models and the algorithm that learns them. By taking advantage of such information, learning hmms/pomdps can be made to generate better solutions and require fewer iterations, while being robust in the face of data reduction. Experimental results, obtained from both simulated and real robot data, demonstrate the effectiveness of the approach.

As a result of this research, we will have a new architecture for mobile robotics that uses both human programming and trial-and-error learning; that plans and learns hierarchically at a variety of levels of abstraction and at di#erent points in the reactive/deliberative spectrum; and that is aware of its own knowledge and lack of knowledge and takes explicit action to gain information. This architecture will enable a revolution in mobile robot applications. 2 B Technical Rationale and Approach B.1 Introduction The theses stated above form the technical rationale for the project. In this section, we elaborate on them. 1. The necessity for learning and programming It is widely understood that there is no free lunch in machine learning. It is formally, technically impossible to predict a future you have never seen unless you have some information that constrains in advance the possible universes you operate in. This insight h