Author name cluster

Andrew Howard

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

NeurIPS Conference 2023 Conference Paper

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

Shuyang Sun
Weijun Wang
Andrew Howard
Qihang Yu
Philip Torr
Liang-Chieh Chen

This paper presents a new mechanism to facilitate the training of mask transformers for efficient panoptic segmentation, democratizing its deployment. We observe that due to the high complexity in the training objective of panoptic segmentation, it will inevitably lead to much higher penalization on false positive. Such unbalanced loss makes the training process of the end-to-end mask-transformer based architectures difficult, especially for efficient models. In this paper, we present ReMaX that adds relaxation to mask predictions and class predictions during the training phase for panoptic segmentation. We demonstrate that via these simple relaxation techniques during training, our model can be consistently improved by a clear margin without any extra computational cost on inference. By combining our method with efficient backbones like MobileNetV3-Small, our method achieves new state-of-the-art results for efficient panoptic segmentation on COCO, ADE20K and Cityscapes. Code and pre-trained checkpoints will be available at https: //github. com/google-research/deeplab2.

PDF Details

ICRA Conference 2010 Conference Paper

Autonomous navigation for BigDog

David Wooden
Matthew Malchano
Kevin Blankespoor
Andrew Howard
Alfred A. Rizzi
Marc H. Raibert

BigDog is a four legged robot with exceptional rough-terrain mobility. In this paper, we equip BigDog with a laser scanner, stereo vision system, and perception and navigation algorithms. Using these sensors and algorithms, BigDog performs autonomous navigation to goal positions in unstructured forest environments. The robot perceives obstacles, such as trees, boulders, and ground features, and steers to avoid them on its way to the goal. We describe the hardware and software implementation of the navigation system and summarize performance. During field tests in unstructured wooded terrain, BigDog reached its goal position 23 of 26 runs and traveled over 130 meters at a time without operator involvement.

Details

ICRA Conference 2008 Conference Paper

Gamma-SLAM: Using stereo vision and variance grid maps for SLAM in unstructured environments

Tim K. Marks
Andrew Howard
Max Bajracharya
Garrison W. Cottrell
Larry H. Matthies

We introduce a new method for stereo visual SLAM (simultaneous localization and mapping) that works in unstructured, outdoor environments. Unlike other grid-based SLAM algorithms, which use occupancy grid maps, our algorithm uses a new mapping technique that maintains a posterior distribution over the height variance in each cell. This idea was motivated by our experience with outdoor navigation tasks, which has shown height variance to be a useful measure of traversability. To obtain a joint posterior over poses and maps, we use a Rao-Blackwellized particle filter: the pose distribution is estimated using a particle filter, and each particle has its own map that is obtained through exact filtering conditioned on the particle’s pose. Visual odometry provides good proposal distributions for the particle pose. In the analytical (exact) filter for the map, we update the sufficient statistics of a gamma distribution over the precision (inverse variance) of heights in each grid cell. We verify the algorithm’s accuracy on two outdoor courses by comparing with ground truth data obtained using electronic surveying equipment. In addition, we solve for the optimal transformation from the SLAM map to georeferenced coordinates, based on a noisy GPS signal. We derive an online version of this alignment process, which can be used to maintain a running estimate of the robot’s global position that is much more accurate than the GPS readings.

Details

ICRA Conference 2008 Conference Paper

Learning long-range terrain classification for autonomous navigation

Max Bajracharya
Benyang Tang
Andrew Howard
Michael J. Turmon
Larry H. Matthies

This paper describes a method for learning the terrain classification of long-range appearance data from short- range, stereo-based geometry, along with a map representation for utilizing this data to improve autonomous off-road navigation. The continuous, online learning method allows the system to constantly adapt to changing terrain and environmental conditions, while the polar-perspective map representation allows the system to effectively plan with stereo data at long ranges. Various evaluations of the long-range classification and improvements in system performance are described, including results from an independent third-party testing team.

Details

IROS Conference 2008 Conference Paper

Real-time stereo visual odometry for autonomous ground vehicles

Andrew Howard

This paper describes a visual odometry algorithm for estimating frame-to-frame camera motion from successive stereo image pairs. The algorithm differs from most visual odometry algorithms in two key respects: (1) it makes no prior assumptions about camera motion, and (2) it operates on dense disparity images computed by a separate stereo algorithm. This algorithm has been tested on many platforms, including wheeled and legged vehicles, and has proven to be fast, accurate and robust. For example, after 4000 frames and 400m of travel, position errors are typically less than 1m (0. 25% of distance traveled). Processing time is approximately 20ms on a 512x384 image. This paper includes a detailed description of the algorithm and experimental evaluation on a variety of platforms and terrain types.

Details

NeurIPS Conference 2007 Conference Paper

Learning Monotonic Transformations for Classification

Andrew Howard
Tony Jebara

A discriminative method is proposed for learning monotonic transforma- tions of the training data while jointly estimating a large-margin classi(cid: 12)er. In many domains such as document classi(cid: 12)cation, image histogram classi(cid: 12)- cation and gene microarray experiments, (cid: 12)xed monotonic transformations can be useful as a preprocessing step. However, most classi(cid: 12)ers only explore these transformations through manual trial and error or via prior domain knowledge. The proposed method learns monotonic transformations auto- matically while training a large-margin classi(cid: 12)er without any prior knowl- edge of the domain. A monotonic piecewise linear function is learned which transforms data for subsequent processing by a linear hyperplane classi(cid: 12)er. Two algorithmic implementations of the method are formalized. The (cid: 12)rst solves a convergent alternating sequence of quadratic and linear programs until it obtains a locally optimal solution. An improved algorithm is then derived using a convex semide(cid: 12)nite relaxation that overcomes initializa- tion issues in the greedy optimization problem. The e(cid: 11)ectiveness of these learned transformations on synthetic problems, text data and image data is demonstrated.

PDF Details

IROS Conference 2004 Conference Paper

Design and use paradigms for Gazebo, an open-source multi-robot simulator

Nathan P. Koenig
Andrew Howard

Simulators have played a critical role in robotics research as tools for quick and efficient testing of new concepts, strategies, and algorithms. To date, most simulators have been restricted to 2D worlds, and few have matured to the point where they are both highly capable and easily adaptable. Gazebo is designed to fill this niche by creating a 3D dynamic multi-robot environment capable of recreating the complex worlds that would be encountered by the next generation of mobile robots. Its open source status, fine grained control, and high fidelity place Gazebo in a unique position to become more than just a stepping stone between the drawing board and real hardware: data visualization, simulation of remote environments, and even reverse engineering of blackbox systems are all possible applications. Gazebo is developed in cooperation with the Player and Stage projects (Gerkey, B. P. , et al. , July 2003), (Gerkey, B. P. , et al. , May 2001), (Vaughan, R. T. , et al. , Oct. 2003), and is available from http://playerstage.sourceforge.net/gazebo/gazebo.html.

Details

ICRA Conference 2004 Conference Paper

Multi-robot Mapping using Manifold Representations

Andrew Howard

This paper introduces a new method for representing two-dimensional maps, and shows how this representation may be applied to concurrent localization and mapping problems involving multiple robots. We introduce the notion of a manifold map; this representation takes maps out of the plane and onto a two-dimensional surface embedded in a higher-dimensional space. Compared with standard planar maps, the key advantage of the manifold representation is self-consistency: manifold maps do not suffer from the 'cross over' problem that planar maps commonly exhibit in environments containing loops. This self-consistency facilitates a number of important autonomous capabilities, including robust retro-traverse, lazy loop closure, active loop closure using robot rendezvous, and, ultimately, autonomous exploration. By way of validation, this paper also includes experimental results obtained using teams of two to four robots in environments ranging in size from 400 m/sup 2/ to 900 m/sup 2/.

Details

JMLR Journal 2004 Journal Article

Probability Product Kernels (Special Topic on Learning Theory)

Tony Jebara
Risi Kondor
Andrew Howard

The advantages of discriminative learning algorithms and kernel machines are combined with generative modeling using a novel kernel between distributions. In the probability product kernel, data points in the input space are mapped to distributions over the sample space and a general inner product is then evaluated as the integral of the product of pairs of distributions. The kernel is straightforward to evaluate for all exponential family models such as multinomials and Gaussians and yields interesting nonlinear kernels. Furthermore, the kernel is computable in closed form for latent distributions such as mixture models, hidden Markov models and linear dynamical systems. For intractable models, such as switching linear dynamical systems, structured mean-field approximations can be brought to bear on the kernel evaluation. For general distributions, even if an analytic expression for the kernel is not feasible, we show a straightforward sampling method to evaluate it. Thus, the kernel permits discriminative learning methods, including support vector machines, to exploit the properties, metrics and invariances of the generative models we infer from each datum. Experiments are shown using multinomial models for text, hidden Markov models for biological data sets and linear dynamical systems for time series data. [abs] [ pdf ] [ ps.gz ] [ ps ]

PDF Details