ואדים אינדלמן (אוירונאוטיקה, טכניון)
יום שלישי, 4.11.2014, 11:30
חדר 337, בניין טאוב למדעי המחשב
In this talk I will describe two recent research efforts addressing challenges in autonomous operation in unknown environments.
First, I will present an approach for multi-robot distributed inference over variables of interest, such as robot trajectories, considering the initial relative pose between the robots and multi-robot data association are both unknown. Assuming robots share with each other informative observations, this inference problem is formulated within an Expectation-Maximization (EM) optimization, performed by each robot separately, alternating between inference over variables of interest and multi-robot data association. To facilitate this process, a common reference frame between the robots should first be established. We show the latter is coupled with determining multi-robot data association, and therefore concurrently infer both using a separate EM optimization. This optimization is performed by each robot starting from several promising initial solutions, converging to locally-optimal hypotheses regarding data association and reference frame transformations. Choosing the best hypothesis in an incremental problem setting is in particular challenging due to high sensitivity to perceptual aliasing and possibly insufficient amount of data. Selecting an incorrect hypothesis introduces outliers and can lead to catastrophic results. To address these challenges we develop a model-selection based approach to choose the most probable hypothesis, while resorting to Chinese Restaurant Process to represent statistical knowledge regarding hypothesis prior probabilities.
In the second part of the talk, I will focus on the problem of planning under uncertainty, with application to mobile robotics. We propose a probabilistic framework in which the robot bases its decisions on the generalized belief, which is a probabilistic description of its own state and of external variables of interest (such as 3D points representing the perceived environment). The approach naturally leads to a dual-layer architecture: an inner estimation layer, which performs inference to predict the outcome of possible decisions, and an outer decisional layer which is in charge of deciding the best action to undertake. The formulation is valid for general cost functions and does not discretize the state or control space, enabling planning in continuous domain. The approach is successfully applied to the problem of uncertainty-constrained exploration, in which the robot has to perform tasks in an unknown environment, while maintaining localization uncertainty within given bounds.
First part is joint work with Nathan Michael and Frank Dellaert; Second part is joint work with Luca Carlone and Frank Dellaert.