Person:

Dellaert, Frank

Permanent Link

https://hdl.handle.net/1853/71202

Associated Organization(s)

Organizational Unit

School of Interactive Computing

Full item page

Publication Search Results

Now showing 1 - 10 of 17

Linear-Time Estimation with Tree Assumed Density Filtering and Low-Rank Approximation

(Georgia Institute of Technology, 2014-09) Ta, Duy-Nguyen ; Dellaert, Frank

We present two fast and memory-efficient approximate estimation methods, targeting obstacle avoidance applications on small robot platforms. Our methods avoid a main bottleneck of traditional filtering techniques, which creates densely correlated cliques of landmarks, leading to expensive time and space complexity. We introduce a novel technique to avoid the dense cliques by sparsifying them into a tree structure and maintain that tree structure efficiently over time. Unlike other edge removal graph sparsification methods, our methods sparsify the landmark cliques by introducing new variables to de-correlate them. The first method projects the current density onto a tree rooted at the same variable at each step. The second method improves upon the first one by carefully choosing a new low-dimensional root variable at each step to replace such that the independence and conditional densities of the landmarks given the trajectory are optimally preserved. Our experiments show a significant improvement in time and space complexity of the methods compared to other standard filtering techniques in worst-case scenarios, with small trade-offs in accuracy due to low-rank approximation errors.
Modern MAP Inference Methods for Accurate and Fast Occupancy Grid Mapping on Higher Order Factor Graphs

(Georgia Institute of Technology, 2014) Dhiman, Vikas ; Kundu, Abhijit ; Dellaert, Frank ; Corso, Jason J.

Using the inverse sensor model has been popular in occupancy grid mapping. However, it is widely known that applying the inverse sensor model to mapping requires certain assumptions that are not necessarily true. Even the works that use forward sensor models have relied on methods like expectation maximization or Gibbs sampling which have been succeeded by more effective methods of maximum a posteriori (MAP) inference over graphical models. In this paper, we propose the use of modern MAP inference methods along with the forward sensor model. Our implementation and experimental results demonstrate that these modern inference methods deliver more accurate maps more efficiently than previously used methods.
Concurrent Filtering and Smoothing: A Parallel Architecture for Real-Time Navigation and Full Smoothing

(Georgia Institute of Technology, 2014) Williams, Stephen ; Indelman, Vadim ; Kaess, Michael ; Roberts, Richard ; Leonard, John J. ; Dellaert, Frank

We present a parallelized navigation architecture that is capable of running in real-time and incorporating long-term loop closure constraints while producing the optimal Bayesian solution. This architecture splits the inference problem into a low-latency update that incorporates new measurements using just the most recent states (filter), and a high-latency update that is capable of closing long loops and smooths using all past states (smoother). This architecture employs the probabilistic graphical models of Factor Graphs, which allows the low-latency inference and high-latency inference to be viewed as sub-operations of a single optimization performed within a single graphical model. A specific factorization of the full joint density is employed that allows the different inference operations to be performed asynchronously while still recovering the optimal solution produced by a full batch optimization. Due to the real-time, asynchronous nature of this algorithm, updates to the state estimates from the high-latency smoother will naturally be delayed until the smoother calculations have completed. This architecture has been tested within a simulated aerial environment and on real data collected from an autonomous ground vehicle. In all cases, the concurrent architecture is shown to recover the full batch solution, even while updated state estimates are produced in real-time.
Eliminating Conditionally Independent Sets in Factor Graphs: A Unifying Perspective based on Smart Factors

(Georgia Institute of Technology, 2014) Carlone, Luca ; Kira, Zsolt ; Beall, Chris ; Indelman, Vadim ; Dellaert, Frank

Factor graphs are a general estimation framework that has been widely used in computer vision and robotics. In several classes of problems a natural partition arises among variables involved in the estimation. A subset of the variables are actually of interest for the user: we call those target variables. The remaining variables are essential for the formulation of the optimization problem underlying maximum a posteriori (MAP) estimation; however these variables, that we call support variables, are not strictly required as output of the estimation problem. In this paper, we propose a systematic way to abstract support variables, defining optimization problems that are only defined over the set of target variables. This abstraction naturally leads to the definition of smart factors, which correspond to constraints among target variables. We show that this perspective unifies the treatment of heterogeneous problems, ranging from structureless bundle adjustment to robust estimation in SLAM. Moreover, it enables to exploit the underlying structure of the optimization problem and the treatment of degenerate instances, enhancing both computational efficiency and robustness.
Towards Planning in Generalized Belief Space

(Georgia Institute of Technology, 2013-12) Indelman, Vadim ; Carlone, Luca ; Dellaert, Frank

We investigate the problem of planning under uncertainty, which is of interest in several robotic applications, ranging from autonomous navigation to manipulation. Recent effort from the research community has been devoted to design planning approaches working in a continuous domain, relaxing the assumption that the controls belong to a finite set. In this case robot policy is computed from the current robot belief (planning in belief space), while the environment in which the robot moves is usually assumed to be known or partially known. We contribute to this branch of the literature by relaxing the assumption of known environment; for this purpose we introduce the concept of generalized belief space (GBS), in which the robot maintains a joint belief over its state and the state of the environment. We use GBS within a Model Predictive Control (MPC) scheme; our formulation is valid for general cost functions and incorporates a dual-layer optimization: the outer layer computes the best control action, while the inner layer computes the generalized belief given the action. The resulting approach does not require prior knowledge of the environment and does not assume maximum likelihood observations. We also present an application to a specific family of cost functions and we elucidate on the theoretical derivation with numerical examples.
Optical Flow Templates for Superpixel Labeling in Autonomous Robot Navigation

(Georgia Institute of Technology, 2013-11) Roberts, Richard ; Dellaert, Frank

Instantaneous image motion in a camera on-board a mobile robot contains rich information about the structure of the environment. We present a new framework, optical flow templates, for capturing this information and an experimental proof-of-concept that labels superpixels using them. Optical flow templates encode the possible optical flow fields due to egomotion for a specific environment shape and robot attitude. We label optical flow in superpixels with the environment shape they image according to how consistent they are with each template. Specifically, in this paper we employ templates highly relevant to mobile robot navigation. Image regions consistent with ground plane and distant structure templates likely indicate free and traversable space, while image regions consistent with neither of these are likely to be nearby objects that are obstacles. We evaluate our method qualitatively and quantitatively in an urban driving scenario, labeling the ground plane, and obstacles such as passing cars, lamp posts, and parked cars. One key advantage of this framework is low computational complexity, and we demonstrate per-frame computation times of 20ms, excluding optical flow and superpixel calculation.
DDF-SAM 2.0: Consistent Distributed Smoothing and Mapping

(Georgia Institute of Technology, 2013-05) Cunningham, Alexander ; Indelman, Vadim ; Dellaert, Frank

This paper presents an consistent decentralized data fusion approach for robust multi-robot SLAM in dan- gerous, unknown environments. The DDF-SAM 2.0 approach extends our previous work by combining local and neigh- borhood information in a single, consistent augmented local map, without the overly conservative approach to avoiding information double-counting in the previous DDF-SAM algo- rithm. We introduce the anti-factor as a means to subtract information in graphical SLAM systems, and illustrate its use to both replace information in an incremental solver and to cancel out neighborhood information from shared summarized maps. This paper presents and compares three summarization techniques, with two exact approaches and an approximation. We evaluated the proposed system in a synthetic example and show the augmented local system and the associated summarization technique do not double-count information, while keeping performance tractable.
Autonomous Flight in GPS-Denied Environments Using Monocular Vision and Inertial Sensors

(Georgia Institute of Technology, 2013-04) Wu, Allen D. ; Johnson, Eric N. ; Kaess, Michael ; Dellaert, Frank ; Chowdhary, Girish

A vision-aided inertial navigation system that enables autonomous flight of an aerial vehicle in GPS-denied environments is presented. Particularly, feature point information from a monocular vision sensor are used to bound the drift resulting from integrating accelerations and angular rate measurements from an Inertial Measurement Unit (IMU) forward in time. An Extended Kalman filter framework is proposed for performing the tasks of vision-based mapping and navigation separately. When GPS is available, multiple observations of a single landmark point from the vision sensor are used to estimate the point’s location in inertial space. When GPS is not available, points that have been sufficiently mapped out can be used for estimating vehicle position and attitude. Simulation and flight test results of a vehicle operating autonomously in a simplified loss-of-GPS scenario verify the presented method.
Primate - Inspired Vehicle Navigation Using Optic Flow and Mental Rotations

(Georgia Institute of Technology, 2013) Arkin, Ronald C. ; Dellaert, Frank ; Srinivasa, Natesh ; Kerwin, Ryan

Robot navigation already has many relatively efficient solutions: reactive control, simultaneous localization and mapping (SLAM), Rapidly-Exploring Random Trees (RRTs), etc. But many primates possess an additional inherent spatial reasoning capability: mental rotation. Our research addresses the question of what role, if any, mental rotations can play in enhancing existing robot navigational capabilities. To answer this question we explore the use of optical flow as a basis for extracting abstract representations of the world, comparing these representations with a goal state of similar format and then iteratively providing a control signal to a robot to allow it to move in a direction consistent with achieving that goal state. We study a range of transformation methods to implement the mental rotation component of the architecture, including correlation and matching based on cognitive studies. We also include a discussion of how mental rotations may play a key role in understanding spatial advice giving, particularly from other members of the species, whether in map-based format, gestures, or other means of communication. Results to date are presented on our robotic platform.
Accurate On-Line 3D Occupancy Grids Using Manhattan World Constraints

(Georgia Institute of Technology, 2012-10) Peasley, Brian ; Birchfield, Stan ; Cunningham, Alexander ; Dellaert, Frank

In this paper we present an algorithm for constructing nearly drift-free 3D occupancy grids of large indoor environments in an online manner. Our approach combines data from an odometry sensor with output from a visual registration algorithm, and it enforces a Manhattan world constraint by utilizing factor graphs to produce an accurate online estimate of the trajectory of a mobile robotic platform. We also examine the advantages and limitations of the octree data structure representation of a 3D environment. Through several experiments in environments with varying sizes and construction we show that our method reduces rotational and translational drift significantly without performing any loop closing techniques.