Optimal trajectory generation for dynamic street scenarios in a Frenét Frame

By Moritz Werling, Julius Ziegler, Sören Kammel, Sebastian Thrun. IEEE International Conference on Robotics and Automation, 2010

852 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/6bda8fc13bda8cffb3bb426a73ce5c12cc0a1760

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

Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks (2016, methodology): “One widely used method aiming to fulfil this objective is introduced by Werling et al [4].”
Local Path Planning for Off-Road Autonomous Driving With Avoidance of Static Obstacles (2012, methodology): “For the transformation between the Cartesian coordinate system and the curvilinear coordinate system, the curvature of the path κ is derived as [18], [27]”
Towards fully autonomous driving: Systems and algorithms (2011, methodology): “For this reason the behavioral layer can switch below a certain velocity threshold to a slightly different trajectory mode generating the lateral trajectory in dependence on the longitudinal movement; see [7] for details.”
Trajectory planning for Bertha — A local, continuous method (2014, methodology): “In Werling et al's method [7], the best trajectory is selected from a finite set.”
ConceptFusion: Open-set Multimodal 3D Mapping (2023, methodology): “Other components of the autonomy stack include a shortest-path global planner, a Frenet [71] local planner for obstacle avoidance, and a Stanley-Controller [72] for trajectory tracking.”
NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking (2024, neutral): “While the idea of sampling and scoring trajectories is well-known [46, 51, 55, 6, 16], it has recently been overlooked in favor of approaches which predict a single trajectory.”
End-To-End Interpretable Neural Motion Planner (2019, methodology): “In sampling-based approaches, a set of trajectories is generated and evaluated against a predefined cost, among which, the one with minimum cost is chosen [27, 30].”
MP3: A Unified Model to Map, Perceive, Predict and Plan (2021, methodology): “A popular approach, for example, is to sample trajectories in Frenet-frame of the goal lane-center, limiting the samples to motions that do not deviate much from the desired lane [1, 45, 46, 50].”
Baidu Apollo EM Motion Planner (2018, methodology): “The SL projection is based on a G2 (continuous curvature derivative) smooth reference line as in [3].”
CommonRoad: Composable benchmarks for motion planning on roads (2017, neutral): “• Acceleration : [44, Sec.”