Avoiding cars and pedestrians using velocity obstacles and motion prediction

@article{Large2004AvoidingCA,
  title={Avoiding cars and pedestrians using velocity obstacles and motion prediction},
  author={Fr{\'e}d{\'e}ric Large and Dizan Vasquez and Thierry Fraichard and Christian Laugier},
  journal={IEEE Intelligent Vehicles Symposium, 2004},
  year={2004},
  pages={375-379}
}
Vehicle navigation in dynamic environments is an important challenge, especially when the motion of the objects populating the environment is unknown. Traditional motion planning approaches are too slow to be applied in real-time to this domain, hence, new techniques are needed. Recently, iterative planning has emerged as a promising approach. Nevertheless, existing iterative methods do not provide a way to estimating the future behaviour of moving obstacles and to use the resulting estimates… 

Figures from this paper

Safe Motion Planning for Autonomous Driving

TLDR
A novel motion planning system is described, which translates high-level navigation goals into low-level actions for controlling a vehicle, and is able to compute a safe and efficient trajectory in a dynamic environment while staying within its lane and avoiding obstacles.

Generalized velocity obstacles

TLDR
This work generalizes the concept of velocity obstacles, which has been used for navigation among dynamic obstacles, and takes into account the constraints of a car-like robot to find controls that will allow collision free navigation in dynamic environments.

Reactive Planning for Assistive Robots

TLDR
A reactive planner that modifies the path in order to avoid pedestrians in the surroundings is proposed that relies on a very accurate model to predict the motion of each pedestrian, i.e., the headed social force model.

Proactive avoidance of moving obstacles for a service robot utilizing a behavior-based control

TLDR
A hierarchical approach for the proactive avoidance of moving objects as it is used on the robot shopping trolley InBOT and a spatio-temporal planner is situated which is able to predict environmental changes and therefore can generate a safe movement sequence accordingly.

Autonomous Driving among Many Pedestrians: Models and Algorithms

TLDR
A planning system for autonomous driving among many pedestrians that combines a POMDP algorithm with the pedestrian motion model and runs in near real time and enables a robot vehicle to drive safely, efficiently, and smoothly among a crowd with a density of nearly one person per square meter.

Robotic motion planning in dynamic, cluttered, uncertain environments

TLDR
A Partially Closed-loop Receding Horizon Control algorithm whose approximation to the DP solution integrates prediction, estimation, and planning while also accounting for chance constraints that arise from the uncertain location of the robot and other moving agents.

Long-term vehicle motion prediction

TLDR
This study proposes in this study a long-term prediction approach based on a combined trajectory classification and particle filter framework and introduces the quaternion-based rotationally invariant longest common subsequence (QRLCS) metric.

Safe and Efficient Navigation in Dynamic Environments

TLDR
This thesis proposes a novel path planning algorithm in environments with dynamic agents with quick planning times and develops an approach that models the joint distribution over future trajectories of all interacting agents in the crowd through a local interaction model that is trained using real human trajectory data.

Robot Motion Planning in Dynamic, Uncertain Environments

TLDR
To approximately solve the stochastic dynamic programming problem that is associated with DUE planning, a partially closed-loop receding horizon control algorithm is presented whose solution integrates prediction, estimation, and planning while also accounting for chance constraints that arise from the uncertain locations of the robot and obstacles.

Path planning for a mobile robot in a dynamic environment

TLDR
Development of algorithms with the integration of path planning by potential field method and Monte Carlo localization method for navigation, obstacle avoidance, and localization of the mobile robot in a dynamic environment like in manufacturing industry is focused on.
...

References

SHOWING 1-10 OF 26 REFERENCES

Towards real-time global motion planning in a dynamic environment using the NLVO concept

TLDR
A novel approach is presented, based on the Non-Linear Velocity Obstacle Concept, that maps the positions of the obstacles and their known or estimated trajectories directly in the space of the velocities admissible by the robot, taking into account its kinematic and dynamics constraints.

Motion planning in dynamic environments: obstacles moving along arbitrary trajectories

  • Z. ShillerF. LargeS. Sekhavat
  • Mathematics
    Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164)
  • 2001
TLDR
The nonlinear velocity obstacle is introduced, which takes into account the shape, velocity and path curvature of the moving obstacle, which elevates the planning strategy to a second order method, compared to the first order avoidance using the linear v-obstacle.

Acquisition of statistical motion patterns in dynamic environments and their application to mobile robot motion planning

  • E. KruseR. GutscheF. Wahl
  • Computer Science
    Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Innovative Robotics for Real-World Applications. IROS '97
  • 1997
TLDR
In this paper, in a real environment, cameras observe the workspace in order to detect obstacle motions and to derive statistical data, and new techniques based on stochastic trajectories to model obstacle behavior are developed.

Real-time motion planning for agile autonomous vehicles

TLDR
This paper proposes a randomized motion planning architecture for dynamical systems in the presence of fixed and moving obstacles that addresses the dynamic constraints on the vehicle's motion, and it provides at the same time a consistent decoupling between low-level control and motion planning.

Time-minimal paths among moving obstacles

  • K. FujimuraH. Samet
  • Computer Science, Mathematics
    Proceedings, 1989 International Conference on Robotics and Automation
  • 1989
TLDR
The concept of accessibility from a point to a moving object is introduced, and it is used to define a graph on a set of moving obstacles that shows if the moving point is able to move faster than any of the obstacles, a time-minimal path is given as a sequence of edges in the graph.

Kinodynamic motion planning amidst moving obstacles

  • R. KindelDavid HsuJ. LatombeS. Rock
  • Computer Science
    Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065)
  • 2000
This paper presents a randomized motion planner for kinodynamic asteroid avoidance problems, in which a robot must avoid collision with moving obstacles under kinematic, dynamic constraints and reach

The lane-curvature method for local obstacle avoidance

  • N. KoR. Simmons
  • Engineering
    Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190)
  • 1998
The lane-curvature method (LCM) presented in this paper is a new local obstacle avoidance method for indoor mobile robots. The method combines curvature-velocity method (CVM) with a new directional

Randomized Kinodynamic Motion Planning with Moving Obstacles

TLDR
A detailed analysis of the planner's convergence rate shows that, if the state×time space satisfies a geometric property called expansiveness, then a slightly idealized version of the implemented planner is guaranteed to find a trajectory when one exists, with probability quickly converging to 1, as the number of milestones increases.

On multiple moving objects

TLDR
This paper explores the motion planning problem for multiple moving objects by assigning priorities to the objects, then planning motions one object at a time, using two-dimensional slices.

Trajectory planning in a dynamic workspace: a 'state-time space' approach

TLDR
This paper addresses trajectory planning in a dynamic workspace, i.e. motion planning for a robot subject to dynamic constraints and moving in a workspace with moving obstacles with a near-time-optimal approach that searches the solution trajectory over a restricted set of canonical trajectories.