Autonomous Driving in Urban Environments: Boss and the Urban Challenge

Urmson, Chris; Anhalt, Joshua; Bagnell, Drew; Baker, Christopher; Bittner, Robert; Clark, Michael; Dolan, John M.; Duggins, David; Galatali, Tugrul; Geyer, Chris; Gittleman, Michele; Harbaugh, Sam; Hebert, Martial; Howard, Thomas M.; Kolski, Sascha; Kelly, Alonzo; Likhachev, Maxim; McNaughton, Matthew; Miller, Nick; Peterson, Kevin; Pilnick, Brian; Rajkumar, R.; Rybski, Paul E.; Salesky, Bryan; Seo, Yongsok; Singh, Sanjiv; Snider, Jarrod M.; Stentz, Anthony; Whittaker, William; Wolkowicki, Ziv; Ziglar, Jason; Bae, Hong; Brown, Thomas; Demitrish, Daniel; Litkouhi, Bakhtiar; Nickolaou, Jim; Sadekar, Varsha; Zhang, Wende; Struble, Joshua; Taylor, Michael; Darms, Michael; Ferguson, Dave

doi:10.1007/978-3-642-03991-1_1

Cited by 542 publications

(694 citation statements)

References 14 publications

Supporting

Mentioning

672

Contrasting

Unclassified

Order By: Relevance

“…The sub-sequence of trajectories is usually computed offline [11,9]. Such methods are widely used in modern, autonomous ground robots including the two highest placing teams for DARPA Urban Challenge and Grand Challenge [28,17,27,26], LAGR [12], UPI [1], and Perceptor [14] programs. We use CONSEQOPT to maximize this function and generate trajectory sequences taking the current environment features.…”

Section: B Mobile Robot Navigationmentioning

confidence: 99%

Contextual Sequence Prediction with Application to Control Library Optimization

Dey¹,

Liu²,

Hebert³

et al. 2012

Robotics: Science and Systems VIII

Self Cite

View full text Add to dashboard Cite

Abstract-Sequence optimization, where the items in a list are ordered to maximize some reward has many applications such as web advertisement placement, search, and control libraries in robotics. Previous work in sequence optimization produces a static ordering that does not take any features of the item or context of the problem into account. In this work, we propose a general approach to order the items within the sequence based on the context (e.g., perceptual information, environment description, and goals). We take a simple, efficient, reduction-based approach where the choice and order of the items is established by repeatedly learning simple classifiers or regressors for each "slot" in the sequence. Our approach leverages recent work on submodular function maximization to provide a formal regret reduction from submodular sequence optimization to simple costsensitive prediction. We apply our contextual sequence prediction algorithm to optimize control libraries and demonstrate results on two robotics problems: manipulator trajectory prediction and mobile robot path planning.

show abstract

Section: B Mobile Robot Navigationmentioning

confidence: 99%

Contextual Sequence Prediction with Application to Control Library Optimization

Dey¹,

Liu²,

Hebert³

et al. 2012

Robotics: Science and Systems VIII

Self Cite

View full text Add to dashboard Cite

show abstract

“…calculateSysFDegLevel(sf ,sf.degRules,sf.subSs) 7: end for 8: end for As stated in [8], autonomous vehicles have various sensor types with different modalities. Since sensors are prone to intermittent faults, using a different sensor is better than duplicating the same type of sensors.…”

Section: Algorithm 1 Degradation Calculationmentioning

confidence: 99%

Adaptive Error and Sensor Management for Autonomous Vehicles: Model-Based Approach and Run-Time System

Frtunikj

Rupanov

Armbruster

et al. 2014

Model-Based Safety and Assessment

View full text Add to dashboard Cite

Abstract. Over the past few years semi-autonomous driving functionality was introduced in the automotive market, and this trend continues towards fully autonomous cars. While in autonomous vehicles data from various types of sensors realize the new highly safety critical autonomous functionality, the already complex system architecture faces the challenge of designing highly reliable and safe autonomous driving system. Since sensors are prone to intermittent faults, using different sensors is better and more cost effective than duplicating the same sensor type because of diversity of reaction of different sensor typesto the same environmental condition. Specifying and validating sensors and providing technical means that enable usage of data from different sensors in case of failures is a challenging, time-consuming and error-prone task for engineers. Therefore, in this paper we present our model-based approach and a runtime system that improves the safety of autonomous driving systems by providing reusable framework managing different sensor setups in a vehicle in a case of a error. Moreover, the solution that we provide enables adaptive graceful degradation and reconfiguration by effective use of the system resources. At the end we explain in an example when and how the approach can be applied.

show abstract

“…Historically, the mapping of features to costs has been performed by simple manual construction of a parameterized function, and then hand tuning various parameters to create a cost function that produces desired behavior. This manual approach has been frequently used whether the cost functions in question describe locations in the world [8,16,17] or actions to be performed [4,11,19]. Unfortunately, this tedious approach typically produces subpar results, potentially leading to subpar autonomous performance.…”

Section: Related Workmentioning

confidence: 99%

Learning Autonomous Driving Styles and Maneuvers from Expert Demonstration

Silver

Bagnell

Stentz

2013

Springer Tracts in Advanced Robotics

Self Cite

View full text Add to dashboard Cite

One of the many challenges in building robust and reliable autonomous systems is the large number of parameters and settings such systems often entail. The traditional approach to this task is simply to have system experts hand tune various parameter settings, and then validate them through simulation, offline playback, and field testing. However, this approach is tedious and time consuming for the expert, and typically produces subpar performance that does not generalize. Machine learning offers a solution to this problem in the form of learning from demonstration. Rather than ask an expert to explicitly encode his own preferences, he must simply demonstrate them, allowing the system to autonomously configure itself accordingly. This work extends this approach to the task of learning driving styles and maneuver preferences for an autonomous vehicle. Head to head experiments in simulation and with a live autonomous system demonstrate that this approach produces better autonomous performance, and with less expert interaction, than traditional hand tuning.

show abstract

Autonomous Driving in Urban Environments: Boss and the Urban Challenge

Cited by 542 publications

References 14 publications

Contextual Sequence Prediction with Application to Control Library Optimization

Contextual Sequence Prediction with Application to Control Library Optimization

Adaptive Error and Sensor Management for Autonomous Vehicles: Model-Based Approach and Run-Time System

Learning Autonomous Driving Styles and Maneuvers from Expert Demonstration

Contact Info

Product

Resources

About