Trajectory planning for Bertha — A local, continuous method

By Julius Ziegler, Philipp Bender, T. Dang, Christoph Stiller. 2014

465 citations recorded by the source corpus.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

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

In Control and Systems Engineering

Citations in the corpus

A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, methodology): “Kalman filtering is sufficient for simple linear models, while the extended and and unscented Kalman filters [186] are used to handle nonlinear dynamic models [187].”
A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning (2017, background): “For instance, in [11], with a horizon length of N =30 , iteration of the optimizer was terminated after 0 .”
Real-time motion planning methods for autonomous on-road driving: State-of-the-art and future research directions (2015, methodology): “Furthermore, most approaches either assume perfect knowledge of the environment (e.g. Aoude et al., 2010b; Bandyopadhyay et al., 2012; Brechtel et al., 2014) or depend on expensive sensing (e.g. Ziegler et al., 2014b) to perceive near-perfect knowledge of the environment and the obstacles.”
A Survey of State-Action Representations for Autonomous Driving (2018, background): “See, for instance, Levine and Koltun (2012); Ziegler et al. (2014); Qian et al. (2016); Sadigh et al. (2016).”
Self-Driving Cars: A Survey (2019, methodology): “ts and environment’s constraints. However, they have high computational cost, because the optimization process takes place at each motion state, and depend on global waypoints [GON16]. Ziegler et al. [ZIE14b] uses a function optimization method for trajectory planning of the self-driving car “Bertha”
End-To-End Interpretable Neural Motion Planner (2019, methodology): “Optimization Based Planners: Motion planning has long been treated as an independent task that uses the outputs of perception and prediction modules to formulate an optimization problem, usually by manually engineering a cost function [4, 10, 20, 36].”
Collision Avoidance and Stabilization for Autonomous Vehicles in Emergency Scenarios (2017, background): “2599783 recent research with Junior and other vehicles such as Bertha [3], [4].”
CommonRoad: Composable benchmarks for motion planning on roads (2017, background): “• Yaw rate : 2 d t , where d is the distance to the lane center or a driving corridor (see [43,”
A Review of Motion Planning Techniques for Automated Vehicles (2016, background): “b) Trajectory optimization from [38], taking into account a vehicle in the other lane.”
Research Advances and Challenges of Autonomous and Connected Ground Vehicles (2019, methodology): “The variational method is a straightforward way to generate a trajectory, which models all the objectives and constraints in the time domain as a non-linear continuous optimization problem [381]– [383].”
The kinematic bicycle model: A consistent model for planning feasible trajectories for autonomous vehicles? (2017, background): “In some actual implementations [3], the low-level controller is provided by the test car OEM as a black-box, with hard limits on the acceptable inputs of this control to prevent the vehicle from leaving its handling envelope.”