Junior: The Stanford entry in the Urban Challenge

By Michael Montemerlo, J. Becker, Suhrid Bhat, Hendrik Dahlkamp, Dmitri A. Dolgov, S. Ettinger, Dirk Hähnel, T. Hildén, G. Hoffmann, Burkhard Huhnke and 15 more. 2008

1,307 citations recorded by the source corpus.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Watch this: Scalable cost-function learning for path planning in urban environments (2016, background): “I. INTRODUCTION The majority of state-of-the-art motion planning systems for autonomous driving applications rely on manually designed cost-functions [1], with recent successful examples given by the competing teams in the DARPA Grand [2] and Urban Challenges [3], [4].”
Probabilistic Analysis of Dynamic Scenes and Collision Risks Assessment to Improve Driving Safety (2011, background): “Recent promising results in more complex scenarios are the CityCars concept [4], the DARPA Urban Challenge [5], [6], or the Google Cars [7].”
Baidu Apollo EM Motion Planner (2018, background): “These approaches can be further divided into hand-tuning decisions ([8], [9], [3]) and model-based decisions ([10], [11]).”
Optimization‐based autonomous racing of 1:43 scale RC cars (2015, methodology): “In [7], several approaches to this problem are presented, for example based on model predictive trajectory generation algorithms [31], modified A-algorithms [32] or RRTs [33].”
Potential Cyberattacks on Automated Vehicles (2015, background): “Moreover, attack trees do not specifically integrate the detection part, which is necessary to assess the probability of success of the attack.”
Aggressive Deep Driving: Combining Convolutional Neural Networks and Model Predictive Control (2017, methodology): “Several examples of this approach can be found in the perception and control architectures utilized in the DARPA Grand Challenge Competitions [1, 2, 3].”
Research Advances and Challenges of Autonomous and Connected Ground Vehicles (2019, background): “The rule-based approach manually speciﬁes a driving action set for different driving context, mostly by the ﬁnite state machine (FSM) or similar frameworks like behavior trees [34], [349].”
Real-time motion planning methods for autonomous on-road driving: State-of-the-art and future research directions (2015, background): “The main advantage of RRTs is the quick exploration of the free space; however, their main drawbacks lie in the jerky paths they create (Murphy and Newman, 2011), as well as in the strong dependence on the nearest neighbour metric for expansion of the tree (Ziegler and Stiller, 2009).”
Apprenticeship learning for motion planning with application to parking lot navigation (2008, background): “(See [10] for a detailed description of Junior.)”
Autoware on Board: Enabling Autonomous Vehicles with Embedded Systems (2018, background): “Self-driving technology has made a significant leap in both theory and practice since prototype autonomous vehicles shown off on the DARPA Urban Challenge projects [26], [31], [32], [33], [34].”
Recent progress in road and lane detection: a survey (2014, methodology): “Some works use multiple algorithms and modalities in the same processing step to achieve enhanced robustness [2,4,28,19,22,21,23,24], and in general such fusion of multiple information sources seems to be critical to achieve reasonable system level performance.”
Behavior Trees in Robotics and AI: An Introduction (2017, methodology): “Some of them used a HFSM[45] decomposing the mission task in multiple subtasks in a hierarchy.”
Perception, Planning, Control, and Coordination for Autonomous Vehicles (2017, methodology): “zones” [42], or merge zones at intersection, and checked against the trajectories of all nearby vehicles to determine a “time to collision”.”
Continuous 3D scan-matching with a spinning 2D laser (2009, methodology): “Another option is the use of a high-speed multielement 3D lidar such as the Velodyne HDL-64E (e.g., [ 6 ], [7]).”
Towards fully autonomous driving: Systems and algorithms (2011, background): “We previously published an overview of Junior, Stanford’s entry in the 2007 DARPA Urban Challenge.[1] This race was a closed-course competition which, while historic and inciting much progress in the field, was not fully representative of the situations that exist in the real world.”
A review of convolutional neural network architectures and their optimizations (2022, background): “For instance, modern smartphones are increasingly performing object recognition (Montremerlo et al. 2008), medical equipment acquisition and patient data analysis (Lee and Verma 2013; Alzubaidi et al.”