Search

This paper describes an algorithm for estimating lane boundaries and curbs from a moving vehicle using noisy observations and a probabilistic model of curvature. The primary contribution of this paper is a curve model we call lateral uncertainty, which describes the uncertainty of a curve estimate along the lateral direction at various points on the curve, and does not attempt to capture uncertainty along the longitudinal direction of the curve. Additionally, our method incorporates expected road curvature information derived from an empirical study of a real road network. Our method is notable in that it accurately captures the geometry of arbitrarily complex lane boundary curves that are not well approximated by straight lines or low-order polynomial curves. Our method operates independently of the direction of travel of the vehicle, and incorporates sensor uncertainty associated with individual observations. We analyze the benefits and drawbacks of the approach, and show results of our algorithm applied to real world data sets.

This paper describes a system for detecting and estimating the properties of multiple travel lanes in an urban road network from calibrated video imagery and laser range data acquired by a moving vehicle. The system operates in real-time in several stages on multiple processors, fusing detected road markings, obstacles, and curbs into a stable non-parametric estimate of nearby travel lanes. The system incorporates elements of a provided piecewise-linear road network as a weak prior. Our method is notable in several respects: it detects and estimates multiple travel lanes; it fuses asynchronous, heterogeneous sensor streams; it handles high-curvature roads; and it makes no assumption about the position or orientation of the vehicle with respect to the road. We analyze the system's performance in the context of the 2007 DARPA Urban Challenge. With five cameras and thirteen lidars, our method was incorporated into a closedloop controller to successfully guide an autonomous vehicle through a 90 km urban course at speeds up to 40 km/h amidst moving traffic., Published in Autonomous Robots, v26 p103-122, 2009.

This paper describes a system for detecting and estimating the properties of multiple travel lanes in an urban road network from calibrated video imagery and laser range data acquired by a moving vehicle. The system operates in real-time in several stages on multiple processors, fusing detected road markings, obstacles, and curbs into a stable non-parametric estimate of nearby travel lanes. The system incorporates elements of a provided piecewise-linear road network as a weak prior. Our method is notable in several respects: it detects and estimates multiple travel lanes; it fuses asynchronous, heterogeneous sensor streams; it handles high-curvature roads; and it makes no assumption about the position or orientation of the vehicle with respect to the road. We analyze the system’s performance in the context of the 2007 DARPA Urban Challenge. With five cameras and thirteen lidars, our method was incorporated into a closed-loop controller to successfully guide an autonomous vehicle through a 90 km urban course at speeds up to 40 km/h amidst moving traffic., United States. Defense Advanced Research Projects Agency

Mid-way through the 2007 DARPA Urban Challenge, MIT's autonomous Land Rover LR3 'Talos' and Team Cornell's autonomous Chevrolet Tahoe 'Skynet' collided in a low-speed accident, one of the first well-documented collisions between two full-size autonomous vehicles. This collaborative study between MIT and Cornell examines the root causes of the collision, which are identified in both teams' system designs. Systems-level descriptions of both autonomous vehicles are given, and additional detail is provided on sub-systems and algorithms implicated in the collision. A brief summary of robot-robot interactions during the race is presented, followed by an in-depth analysis of both robots' behaviors leading up to and during the Skynet-Talos collision. Data logs from the vehicles are used to show the gulf between autonomous and human-driven vehicle behavior at low speeds and close proximities. Contributing factors are shown to be: (1) difficulties in sensor data association leading to phantom obstacles and an inability to detect slow moving vehicles, (2) failure to anticipate vehicle intent, and (3) an over emphasis on lane constraints versus vehicle proximity in motion planning. Eye contact between human road users is a crucial communications channel for slow-moving close encounters between vehicles. Inter-vehicle communication may play a similar role for autonomous vehicles; however, there are availability and denial-of-service issues to be addressed., Published in Journal of Field Robotics, Special Issue on the DARPA Urban Challenge, Part III, v25 n10 p775-807, Oct 2008. Parepared in cooperation with Cornell University, Ithaca, NY. U.S. Government or Federal Rights License. The original document contains color images.

We describe an indoor, room-level location discovery method based on spatial variations in "wifi signatures," i.e., MAC addresses and signal strengths of existing wireless access points. The principal novelty of our system is its organic nature; it builds signal strength maps from the natural mobility and lightweight contributions of ordinary users, rather than dedicated effort by a team of site surveyors. Whenever a user's personal device observes an unrecognized signature, a GUI solicits the user's location. The resulting location-tagged signature or "bind" is then shared with other clients through a common database, enabling devices subsequently arriving there to discover location with no further user contribution. Realizing a working system deployment required three novel elements: (1) a human-computer interface for indicating location over intervals of varying duration; (2) a client-server protocol for pre-fetching signature data for use in localization; and (3) a location-estimation algorithm incorporating highly variable signature data. We describe an experimental deployment of our method in a nine-story building with more than 1,400 distinct spaces served by more than 200 wireless access points. At the conclusion of the deployment, users could correctly localize to within 10 meters 92 percent of the time.

We describe a new method for wide-area, non-metrical robot navigationwhich enables useful, purposeful motion indoors. Our method has twophases: a training phase, in which a human user directs a wheeledrobot with an attached camera through an environment while occasionallysupplying textual place names; and a navigation phase in which theuser specifies goal place names (again as text), and the robot issueslow-level motion control in order to move to the specified place. We show thatdifferences in the visual-field locations and scales of features matched acrosstraining and navigation can be used to construct a simple and robust controlrule that guides the robot onto and along the training motion path.Our method uses an omnidirectional camera, requires approximateintrinsic and extrinsic camera calibration, and is capable of effective motioncontrol within an extended, minimally-prepared building environment floorplan.We give results for deployment within a single building floor with 7 rooms, 6corridor segments, and 15 distinct place names.

This technical report describes Team MIT’s approach to theDARPA Urban Challenge. We have developed a novel strategy forusing many inexpensive sensors, mounted on the vehicle periphery,and calibrated with a new cross-­modal calibrationtechnique. Lidar, camera, and radar data streams are processedusing an innovative, locally smooth state representation thatprovides robust perception for real­ time autonomous control. Aresilient planning and control architecture has been developedfor driving in traffic, comprised of an innovative combination ofwell­proven algorithms for mission planning, situationalplanning, situational interpretation, and trajectory control. These innovations are being incorporated in two new roboticvehicles equipped for autonomous driving in urban environments,with extensive testing on a DARPA site visit course. Experimentalresults demonstrate all basic navigation and some basic trafficbehaviors, including unoccupied autonomous driving, lanefollowing using pure-­pursuit control and our local frameperception strategy, obstacle avoidance using kino-­dynamic RRTpath planning, U-­turns, and precedence evaluation amongst othercars at intersections using our situational interpreter. We areworking to extend these approaches to advanced navigation andtraffic scenarios.

We describe an algorithm that takes as inputs a coarse3D model of an environment, and a video sequence acquiredwithin the environment, and produces as output an estimateof the cameraÂ’s 6-DOF egomotion expressed in the coordinatesof the 3D model. Our method has several novelaspects: it performs line-based structure-from-motion; italigns the local line constellation to the known model; andit uses off-line visibility analysis to dramatically acceleratethe alignment process.We present simulation results demonstrating themethodÂ’s operation in a multi-room environment. We showthat the method can estimate metric egomotion accuratelyand could be used for for many minutes of operation andthousands of video frames.

This paper describes a method for bringing two videos (recorded at different times) into spatiotemporal alignment, then comparing and combining corresponding pixels for applications such as background subtraction, compositing, and increasing dynamic range. We align a pair of videos by searching for frames that best match according to a robust image registration process. This process uses locally weighted regression to interpolate and extrapolate high-likelihood image correspondences, allowing new correspondences to be discovered and refined. Image regions that cannot be matched are detected and ignored, providing robustness to changes in scene content and lighting, which allows a variety of new applications.

Recovering three-dimensional information from two-dimensional images is the fundamental goal of stereo techniques. The problem of recovering depth (three-dimensional information) from a set of images is essentially the correspondence problem: Given a point in one image, find the corresponding point in each of the other images. Finding potential correspondences usually involves matching some image property. If the images are from nearby positions, they will vary only slightly, simplifying the matching process. Once a correspondence is known, solving for the depth is simply a matter of geometry. Real images are composed of noisy, discrete samples, therefore the calculated depth will contain error. This error is a function of the baseline or distance between the images. Longer baselines result in more precise depths. This leads to a conflict: short baselines simplify the matching process, but produce imprecise results; long baselines produce precise results, but complicate the matching process. In this paper, we present a method for generating dense depth maps from large sets (1000's) of images taken from arbitrary positions. Long baseline images improve the accuracy. Short baseline images and the large number of images greatly simplifies the correspondence problem, removing nearly all ambiguity. The algorithm presented is completely local and for each pixel generates an evidence versus depth and surface normal distribution. In many cases, the distribution contains a clear and distinct global maximum. The location of this peak determines the depth and its shape can be used to estimate the error. The distribution can also be used to perform a maximum likelihood fit of models directly to the images. We anticipate that the ability to perform maximum likelihood estimation from purely local calculations will prove extremely useful in constructing three dimensional models from large sets of images.