Potential Negative Obstacle Detection by Occlusion Labeling

Nicholas Heckman, Jean-François Lalonde, Nicolas Vandapel, and Martial Hebert

Abstract

In this paper, we present an approach for potential negative obstacle detection based on missing data interpretation that extends traditional techniques driven by data only which capture the occupancy of the scene. The approach is decomposed into three steps: three-dimensional (3-D) data accumulation and low level classification, 3-D occluder propagation, and context-based occlusion labeling. The approach is validated using logged laser data collected in various outdoor natural terrains and also demonstrated live on-board the Demo-III eXperimental Unmanned Vehicle (XUV).

Citation

Nicholas Heckman, Jean-François Lalonde, Nicolas Vandapel and Martial Hebert. Potential Negative Obstacle Detection by Occlusion Labeling. IEEE/RSJ International Conference on Intelligent Robots and Systems, October 2007 [PDF], [BibTeX]

Natural Terrain Classification using Three-Dimensional Ladar Data for Ground Robot Mobility

Jean-François Lalonde, Nicolas Vandapel, Daniel F. Huber and Martial Hebert

Abstract

In recent years, much progress has been made in outdoor autonomous navigation. However, safe navigation is still a daunting challenge in terrain containing vegetation. In this paper, we focus on the segmentation of ladar data into three classes using local three-dimensional point cloud statistics. The classes are: "scatter" to represent porous volumes such as grass and tree canopy; "linear" to capture thin objects like wires or tree branches, and finally "surface" to capture solid objects like ground surface, rocks, or large trunks. We present the details of the proposed method, and the modifications we made to implement it on-board an autonomous ground vehicle for real-time data processing. Finally, we present results produced from different stationary laser sensors and from field tests using an unmanned ground vehicle.

Citation

Jean-François Lalonde, Nicolas Vandapel, Daniel F. Huber and Martial Hebert. Natural Terrain Classification using Three-Dimensional Ladar Data for Ground Robot Mobility. Journal of Field Robotics, 23(10):839--861, October 2006. [PDF], [BibTeX]

Mobile Robot Programming in Education

Jean-François Lalonde, Christopher P. Bartley and Illah Nourbakhsh

Abstract

The Mobile Robot Programming course has been taught at Carnegie Mellon University for the past twelve years. It is a problem-driven class designed for students with little or no experience with robots. In this paper, we first present the current status of the class, and show how it improves the education and training of students in a robotics curriculum by giving them a hands-on experience with a real robot. We show that, in addition to core subjects such as perception, action and cognition, students also have the opportunity to learn advanced topics such as reinforcement learning and multi-robot coordination. We then discuss the evolution of the class under general categories: hardware and programming environment, team experiments, and assignments. We present important lessons learned in each category, and how they affect the learning experience of participating students. We conclude by discussing future opportunities.

Citation

Jean-François Lalonde, Christopher P. Bartley and Illah Nourbakhsh. Mobile Robot Programming in Education. International Conference on Robotics and Automation, 2006. [PDF], [BibTeX]

Talk

Download the slides from the talk presented at ICRA'06 in [MS Powerpoint (2.5 MB)] and [PDF (1.4 MB)].

Synthesizing Environment Maps from a Single Image

Jean-François Lalonde, and Alexei A. Efros

Abstract

Environment mapping is a popular technique for creating consistent lighting when compositing a virtual object into a real scene. However, capturing an environment map usually requires physical access to the scene to obtain illumination measurements. But what if all one has available is a single photograph of the scene? In this paper, we study techniques for synthesizing plausible environment maps from a single image. By analogy with texture synthesis, the goal is to use the small amount of available data to generate an environment map that would be likely to have come from that scene. In particular, we are interested in understanding the role of geometric information in constructing visually realistic environment maps. To this end, we implement several environment synthesis strategies that employ varying amounts of 3D scene geometry information. We measure the quality of the synthesized results by using human subjects to evaluate the appearance of objects illuminated with different environment maps, in still images as well as in video.

Citation

Jean-François Lalonde, and Alexei A. Efros. Synthesizing Environment Maps from a Single Image. Tech. report CMU-RI-TR-10-24, Robotics Institute, Carnegie Mellon University, July, 2010. [PDF], [BibTeX]

Automatic Three-Dimensional Point Cloud Processing for Forest Inventory

Jean-François Lalonde, Nicolas Vandapel and Martial Hebert

Abstract

In this paper, we propose an approach that enables automatic, fast and accurate tree trunks segmentation from three-dimensional (3-D) laser data. Results have been demonstrated in real-time on-board a ground mobile robot. In addition, we propose an approach to estimate tree diameter at breast height (dbh) that was tested off-line on a variety of ground laser scanner data. Results are also presented for detection of tree trunks in aerial laser data. The underlying techniques using in all cases rely on 3-D geometry analysis of point clouds and geometric primitives fitting.

Citation

Jean-François Lalonde, Nicolas Vandapel and Martial Hebert. Automatic Three-Dimensional Point Cloud Processing for Forest Inventory. Tech. report CMU-RI-TR-06-21, Robotics Institute, Carnegie Mellon University, July, 2006. [PDF], [BibTeX]

Augmented-Reality Navigation System for Ground Vehicles (French Only)

Jean-François Lalonde and Jean-Philippe Lajoie-Dorval

Abstract

The goal of this project is to identify important concepts related to the design of augmented-reality navigation systems for ground vehicles. To do so, we first present a state of the current existing technologies, especially the head-up and head-mounted displays. We then present a prototype that has been developed to simulate the system. This allows the study of important factors related to the graphical display of information to the user. The system is tested using various scenarios illustrating its use. Finally, we also developed a real prototype, using a commercial GPS, IMU and webcam. We then apply the algorithms developed previously to this data, and analyze the effect of noise on the end result. Finally, some improvements to the system are proposed. [PDF]