Safe Motion Planning for Autonomous Driving

  title={Safe Motion Planning for Autonomous Driving},
  author={Micah Wylde},
Self-driving cars have the potential to revolutionize transportation by making it cheaper, safer, and more efficient. In this thesis we describe a novel motion planning system, which translates high-level navigation goals into low-level actions for controlling a vehicle. Specifically, the motion planning system is responsible for choosing at each time step an appropriate velocity and steering angle, which can then be implemented by the driving hardware or simulator. Our planner is able to… 



Motion planning in urban environments

This approach combines a model‐predictive trajectory generation algorithm for computing dynamically feasible actions with two higher level planners for generating long‐range plans in both on‐road and unstructured areas of the environment.

Smooth trajectory planning for fully automated passengers vehicles - spline and clothoid based methods and its simulation

This chapter addresses the problem of fully automated operation of trajectory planning methods by proposing an approach that consists of introducing a velocity planning stage to generate adequate time sequences for usage in the interpolating curve planners.

Optimal and Efficient Path Planning for Unknown and Dynamic Environments

The task of planning trajectories for a mobile robot has received considerable attention in the research literature, but less attention has been paid to the problem of unknown or partially-known environments.

Autonomous driving in urban environments: Boss and the Urban Challenge

This dissertation aims to provide a history of web exceptionalism from 1989 to 2002, a period chosen in order to explore its roots as well as specific cases up to and including the year in which descriptions of “Web 2.0” began to circulate.

Path following for autonomous vehicle navigation with inherent safety and dynamics margin

This paper addresses the path following problem for autonomous Ackermann-like vehicle navigation. A control strategy that takes into account both kinodynamic and configuration space constraints of

Planning Long Dynamically-Feasible Maneuvers for Autonomous Vehicles

An algorithm for generating complex dynamically-feasible maneuvers for autonomous vehicles traveling at high speeds over large distances based on performing anytime incremental search on a multiresolution, dynamically- Feasible lattice state space is presented.

Detection, prediction, and avoidance of dynamic obstacles in urban environments

After detecting a dynamic obstacle, the approach exploits structure in the environment where possible to generate a set of likely hypotheses for the future behavior of the obstacle and efficiently incorporates these hypotheses into the planning process to produce safe actions.

Incremental Learning for Motion Prediction of Pedestrians and Vehicles

This thesis proposes a novel extension to Hidden Markov Models which allows simultaneous learning and utilization of the model, and incrementally builds a topological map – representing the model's structure – and reestimates the model’s parameters.

Object Detection and Tracking for Autonomous Navigation in Dynamic Environments

This work addresses the problem of vision-based navigation in busy inner-city locations, using a stereo rig mounted on a mobile platform that combines classical geometric world mapping with object category detection and tracking and recovers the objects’ trajectories.

Anytime Dynamic A*: An Anytime, Replanning Algorithm

A graph-based planning and replanning algorithm able to produce bounded suboptimal solutions in an anytime fashion that combines the benefits of anytime and incremental planners to provide efficient solutions to complex, dynamic search problems.