Brain on Fire (original) (raw)

Towards fully autonomous driving: Systems and algorithms

2011

In order to achieve autonomous operation of a vehicle in urban situations with unpredictable traffic, several realtime systems must interoperate, including environment perception, localization, planning, and control. In addition, a robust vehicle platform with appropriate sensors, computational hardware, networking, and software infrastructure is essential.

The DARPA grand challenge - development of an autonomous vehicle

2004

The DARPA Grand Challenge (DGC) was an opportunity to test autonomous vehicles in a competitive situation. In addition to intelligent behaviour, the participating vehicles must also exhibit ruggedness and endurance in order to survive the fast ride over rough terrain ("win with the software -lose with the hardware"). The SciAutonics teams decided to use compact and agile vehicles that employ proven mechanical designs very suitable for the desert environment. 4-wheel drive ensures robust controllability even in slippery ground, and a roll cage protects the vehicle components from damage in case of a collision. The control system relies primarily on a differential GPS (Starfire) and a set of inertial sensors for navigating between the given set of waypoints. A sensor suite using infrared laser (LIDAR) and ultrasound sensing provides the capability of obstacle avoidance and path following. This paper shows the components of the vehicle and results from driving at the DGC.

Argos: Princeton University's entry in the 2009 Intelligent Ground Vehicle Competition

Intelligent Robots and Computer Vision XXVII: Algorithms and Techniques, 2010

The Princeton IGVC team consists of members of Princeton Autonomous Vehicle Engineering (PAVE ), Princeton University's undergraduate student-led robotics research group. Our team builds upon PAVE 's experience in robotics competitions, including participation in the 2005 DARPA Grand Challenge [1], the 2007 DARPA Urban Challenge [9] and the 2008 Intelligent Ground Vehicle Competition (IGVC) [2]. Our team placed third overall and won rookie-of-the-year in the 2008 IGVC, placing 1st, 4th and 6th in the Design, Navigation and Autonomous challenges, respectively. Argos, our entry in the 2009 IGVC, is an all-new robot based on improvements from 2008. We believe that Argos and the Princeton Team will once again be competitive in the 2009 IGVC.

The SmartTer-a vehicle for fully autonomous navigation and mapping in outdoor environments

The driving factor for the development of the vehicle presented in this paper was to construct a hardware platform that allows to perform the tasks of environment mapping and autonomous navigation in large scale outdoor environments. Our robot is based on a standard Smart car that has been equipped with five distance laser sensors, three cameras, a differential GPS, an Inertial Measurement Unit (IMU), an optical gyroscope and four computers. The car's systems states are directly accessed through the vehicle's CAN bus. Localization and Navigation are realized by fusing all available sensory information in a probabilistic way. This allows for high precision localization and dynamic local and global path planning. Using the 3D point clouds extracted from the rotating lasers and the omnidirectional image the smartTer is able to consistently register the 3D maps and analyse the scene for regions of interest.

Exploring Key Technologies in Autonomous Vehicles

International Journal of Science and Research (IJSR) ISSN: 2319-7064, 2019

This paper dives deep into the technologies used in Autonomous Vehicles. The Global Positioning System (GPS) is a key technology employed by autonomous cars. It is a satellite-based navigation system that determines the exact location of an object. Another technology used by autonomous cars is cameras, which are utilized to detect road signs, identify red lights, and determine lanes on the road, among other functions. Typically, the digital images of the road are presented as unrelated pixels, and this data is structured for better utilization. The algorithm for lane detection interprets this data in four basic steps: preprocessing, feature detection, fitting, and tracking. The other two technologies detailed in this paper are RADAR (Radio Detection and Ranging) and LiDAR (Light Imaging, Detection, and Ranging). RADAR technology uses radio waves to identify objects on the road and is effective in any type of weather conditions. Contrastingly, LiDAR is a laser analyzing device that allows 3D mapping of the surroundings of the vehicle. Unlike RADAR, LiDAR utilizes lasers instead of radio waves.

Lessons Learned from Deploying Autonomous Vehicles at UC San Diego

Field and Service Robotics, 2021

While most autonomous driving efforts reported are directed for general driving and mainly on major roads, there are numerous applications for autonomous vehicles for last mile mobility-from person mobility and mail delivery to flexible recharging of cars in parking structures. Over the last year, we have designed vehicles for the micro-mobility challenge. Our approach was based on adoption of the open source Autoware system. The system was taken as a starting point for the design of a robust solution. Proposed requirements include a robust control design, a shift towards increased use of image data over LiDAR data, handling of a richer set of vehicles / pedestrians in a last mile scenario, and overall system characterization and evaluation. We present an overview of the overall design and the design decisions for construction of vehicles for last-mile delivery.

Kratos: Princeton University's entry in the 2008 Intelligent Ground Vehicle Competition

Intelligent Robots and Computer Vision XXVI: Algorithms and Techniques, 2009

In this paper we present Kratos, an autonomous ground robot capable of static obstacle field navigation and lane following. A sole color stereo camera provides all environmental data. We detect obstacles by generating a 3D point cloud and then searching for nearby points of differing heights, and represent the results as a cost map of the environment. For lane detection we merge the output of a custom set of filters and iterate the RANSAC algorithm to fit parabolas to lane markings. Kratos' state estimation is built on a square root central difference Kalman filter, incorporating input from wheel odometry, a digital compass, and a GPS receiver. A 2D A* search plans the straightest optimal path between Kratos' position and a target waypoint, taking vehicle geometry into account. A novel C++ wrapper for Carnegie Mellon's IPC framework provides flexible communication between all services. Testing showed that obstacle detection and path planning were highly effective at generating safe paths through complicated obstacle fields, but that Kratos tended to brush obstacles due to the proportional law control algorithm cutting turns. In addition, the lane detection algorithm made significant errors when only a short stretch of a lane line was visible or when lighting conditions changed. Kratos ultimately earned first place in the Design category of the Intelligent Ground Vehicle Competition, and third place overall.

Odin: Team VictorTango's entry in the DARPA Urban Challenge

Journal of Field Robotics, 2008

The DARPA Urban Challenge required robotic vehicles to travel more than 90 km through an urban environment without human intervention and included situations such as stop intersections, traffic merges, parking, and roadblocks. Team VictorTango separated the problem into three parts: base vehicle, perception, and planning. A Ford Escape outfitted with a custom drive-by-wire system and computers formed the basis for Odin. Perception used laser scanners, global positioning system, and a priori knowledge to identify obstacles, cars, and roads. Planning relied on a hybrid deliberative/reactive architecture to analyze the situation, select the appropriate behavior, and plan a safe path. All vehicle modules communicated using the JAUS (Joint Architecture for Unmanned Systems) standard. The performance of these components in the Urban Challenge is discussed and successes noted. The result of VictorTango's work was successful completion of the Urban Challenge and a third-place finish. C 2008 Wiley Periodicals, Inc.

Unmanned vehicles come of age: The DARPA grand challenge

Computer, 2000

P u b l i s h e d b y t h e I E E E C o m p u t e r S o c i e t y While the DARPA Grand Challenge has revitalized interest in intelligent highway systems, autonomous vehicles, and sensing technology, a host of other novel issues afford interesting design and computerengineering challenges for the future.