Sam Prentice

Hierarchical classification and feature reduction for fast face detection with support vector machines

We present a two-step method to speed-up object detection systems in computer vision that use support vector machines as classifiers. In the first step we build a hierarchy of classifiers. On the bottom level, a simple and fast linear classifier analyzes the whole image and rejects large parts of the background. On the top level, a slower but more accurate classifier performs the final detection. We propose a new method for automatically building and training a hierarchy of classifiers. In the second step we apply feature reduction to the top level classifier by choosing relevant image features according to a measure derived from statistical learning theory. Experiments with a face detection system show that combining feature reduction with hierarchical classification leads to a speed-up by a factor of 335 with similar classification performance.

Planning in information space for a quadrotor helicopter in a GPS-denied environment

This paper describes a motion planning algorithm for a quadrotor helicopter flying autonomously without GPS. Without accurate global positioning, the vehicles ability to localize itself varies across the environment, since different environmental features provide different degrees of localization. If the vehicle plans a path without regard to how well it can localize itself along that path, it runs the risk of becoming lost. We use the Belief Roadmap (BRM) algorithm [1], an information-space extension of the Probabilistic Roadmap algorithm, to plan vehicle trajectories that incorporate sensing. We show that the original BRM can be extended to use the Unscented Kalman Filter (UKF), and describe a sampling algorithm that minimizes the number of samples required to find a good path. Finally, we demonstrate the BRM path- planning algorithm on the helicopter, navigating in an indoor environment with a laser range-finder.

RANGE–Robust autonomous navigation in GPS-denied environments

This paper addresses the problem of autonomous navigation of a micro air vehicle (MAV) in GPS-denied environments. We present experimental validation and analysis for our system that enables a quadrotor helicopter, equipped with a laser range finder sensor, to autonomously explore and map unstructured and unknown environments. The key challenge for enabling GPS-denied flight of a MAV is that the system must be able to estimate its position and velocity by sensing unknown environmental structure with sufficient accuracy and low enough latency to stably control the vehicle. Our solution overcomes this challenge in the face of MAV payload limitations imposed on sensing, computational, and communication resources. We first analyze the requirements to achieve fully autonomous quadrotor helicopter flight in GPS-denied areas, highlighting the differences between ground and air robots that make it difficult to use algorithms developed for ground robots. We report on experiments that validate our solutions to key challenges, namely a multilevel sensing and control hierarchy that incorporates a high-speed laser scan-matching algorithm, data fusion filter, high-level simultaneous localization and mapping, and a goal-directed exploration module. These experiments illustrate the quadrotor helicopters ability to accurately and autonomously navigate in a number of large-scale unknown environments, both indoors and in the urban canyon. The system was further validated in the field by our winning entry in the 2009 International Aerial Robotics Competition, which required the quadrotor to autonomously enter a hazardous unknown environment through a window, explore the indoor structure without GPS, and search for a visual target.

The Belief Roadmap: Efficient Planning in Belief Space by Factoring the Covariance

When a mobile agent does not know its position perfectly, incorporating the predicted uncertainty of future position estimates into the planning process can lead to substantially better motion performance. However, planning in the space of probabilistic position estimates, or belief space, can incur a substantial computational cost. In this paper, we show that planning in belief space can be performed efficiently for linear Gaussian systems by using a factored form of the covariance matrix. This factored form allows several prediction and measurement steps to be combined into a single linear transfer function, leading to very efficient posterior belief prediction during planning. We give a belief-space variant of the probabilistic roadmap algorithm called the belief roadmap (BRM) and show that the BRM can compute plans substantially faster than conventional belief space planning. We conclude with performance results for an agent using ultra-wide bandwidth radio beacons to localize and show that we can efficiently generate plans that avoid failures due to loss of accurate position estimation.

Estimation, planning, and mapping for autonomous flight using an RGB-D camera in GPS-denied environments

RGB-D cameras provide both color images and per-pixel depth estimates. The richness of this data and the recent development of low-cost sensors have combined to present an attractive opportunity for mobile robotics research. In this paper, we describe a system for visual odometry and mapping using an RGB-D camera, and its application to autonomous flight. By leveraging results from recent state-of-the-art algorithms and hardware, our system enables 3D flight in cluttered environments using only onboard sensor data. All computation and sensing required for local position control are performed onboard the vehicle, reducing the dependence on an unreliable wireless link to a ground station. However, even with accurate 3D sensing and position estimation, some parts of the environment have more perceptual structure than others, leading to state estimates that vary in accuracy across the environment. If the vehicle plans a path without regard to how well it can localize itself along that path, it runs the risk of becoming lost or worse. We show how the belief roadmap algorithm prentice2009belief, a belief space extension of the probabilistic roadmap algorithm, can be used to plan vehicle trajectories that incorporate the sensing model of the RGB-D camera. We evaluate the effectiveness of our system for controlling a quadrotor micro air vehicle, demonstrate its use for constructing detailed 3D maps of an indoor environment, and discuss its limitations.

The Belief Roadmap: Efficient Planning in Linear POMDPs by Factoring the Covariance

In this paper we address the problem of trajectory planning with imperfect state information. In many real-world domains, the position of a mobile agent cannot be known perfectly; instead, the agent maintains a probabilistic belief about its position. Planning in these domains requires computing the best trajectory through the space of possible beliefs. We show that planning in belief space can be done efficiently for linear Gaussian systems by using a factored form of the covariance matrix. This factored form allows several prediction and measurement steps to be combined into a single linear transfer function, leading to very efficient posterior belief prediction during planning. We give a belief-space variant of the Probabilistic Roadmap algorithm called the Belief Roadmap (BRM) and show that the BRM can compute plans substantially faster than conventional belief space planning. We also show performance results for planning a path across MIT campus without perfect localization.

Learning predictive terrain models for legged robot locomotion

Legged robots require accurate models of their environment in order to plan and execute paths. We present a probabilistic technique based on Gaussian processes that allows terrain models to be learned and updated efficiently using sparse approximation techniques. The major benefit of our terrain model is its ability to predict elevations at unseen locations more reliably than alternative approaches, while it also yields estimates of the uncertainty in the prediction. In particular, our nonstationary Gaussian process model adapts its covariance to the situation at hand, allowing more accurate inference of terrain height at points that have not been observed directly. We show how a conventional motion planner can use the learned terrain model to plan a path to a goal location, using a terrain-specific cost model to accept or reject candidate footholds. In experiments with a real quadruped robot equipped with a laser range finder, we demonstrate the usefulness of our approach and discuss its benefits compared to simpler terrain models such as elevations grids.

Reliable Dynamic Motions for a Stiff Quadruped

We present a kinodynamic planning methodology for a high-impedance quadruped robot to negotiate a wide variety of terrain types with high reliability. We achieve motion types ranging from dynamic, double-support lunges for efficient locomotion over extreme obstacles to careful, deliberate foothold and body pose selections which allow for precise foothold placement on rough or intermittent terrain.

On the Design and Use of a Micro Air Vehicle to Track and Avoid Adversaries

The MAV ’08 competition focused on the problem of using air and ground vehicles to locate and rescue hostages being held in a remote building. To execute this mission, a number of technical challenges were addressed, including designing the micro air vehicle (MAV), using the MAV to geo-locate ground targets, and planning the motion of ground vehicles to reach the hostage location without detection. In this paper, we describe the complete system designed for the MAV ’08 competition, and present our solutions to three technical challenges that were addressed within this system. First, we summarize the design of our MAV, focusing on the navigation and sensing payload. Second, we describe the vision and state estimation algorithms used to track ground features, including stationary obstacles and moving adversaries, from a sequence of images collected by the MAV. Third, we describe the planning algorithm used to generate motion plans for the ground vehicles to approach the hostage building undetected by adversaries; these adversaries are tracked by the MAV from the air. We examine different variants of a search algorithm and describe their performance under different conditions. Finally, we provide results of our system’s performance during the mission execution.

RANGE - robust autonomous navigation in GPS-denied environments

This video highlights our system that enables a Micro Aerial Vehicle (MAV) to autonomously explore and map unstructured and unknown GPS-denied environments. While mapping and exploration solutions are now well-established for ground vehicles, air vehicles face unique challenges which have hindered the development of similar capabilities. Although there has been recent progress toward sensing, control, and navigation techniques for GPS-denied flight, there have been few demonstrations of stable, goal-directed flight in real-world environments. Our system leverages a multi-level sensing and control hierarchy that matches the computational complexity of the component algorithms with the real-time needs of a MAV to achieve autonomy in unconstrained environments.