Obstacle avoidance

Related papers: 20

About

Obstacle avoidance is the capability of a robot or autonomous system to detect objects in its environment and maneuver around them without collision. It encompasses both the perception of obstacles—using sensors such as ultrasonic range finders, cameras, or laser scanners—and the generation of safe motion commands in real time. Core techniques include artificial potential fields, which model obstacles as repulsive forces and goals as attractive ones; vector field histograms, which translate sensor readings into navigable directions; and velocity obstacle methods, which reason about collision risks directly in velocity space. These approaches apply equally to mobile ground robots, robotic manipulators, aerial vehicles, and assistive devices like powered wheelchairs. Modern methods increasingly leverage deep reinforcement learning and end-to-end learned policies to handle complex, dynamic, and unstructured environments. Obstacle avoidance is foundational to autonomous robotics because safe operation in real-world settings—among humans, moving objects, and unpredictable terrain—depends entirely on a robot's ability to perceive and react to hazards reliably and without human intervention.

Top Cited Papers

Real-Time Obstacle Avoidance for Manipulators and Mobile Robots

Oussama Khatib

Citations: 7533 • 1986

The vector field histogram-fast obstacle avoidance for mobile robots

J. Borenstein, Yoram Koren

Citations: 2278 • 1991

Motion Planning in Dynamic Environments Using Velocity Obstacles

Paolo Fiorini, Zvi Shiller

Citations: 1930 • 1998

Real-time obstacle avoidance for manipulators and mobile robots

Oussama Khatib

Citations: 1684 • 2005

Real-Time Obstacle Avoidance for Manipulators and Mobile Robots

Oussama Khatib

Citations: 1557 • 1986

Real-time obstacle avoidance for fast mobile robots

J. Borenstein, Yoram Koren

Citations: 1254 • 1989

Obstacle avoidance and navigation in the real world by a seeing robot rover

Hans Moravec

Citations: 857 • 2018

Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation

Giuseppe Paolo, Ming Liu

Citations: 800 • 2017

Vision and navigation for the Carnegie-Mellon Navlab

C. Thorpe, Martial Hebert, Takeo Kanade, Steven A. Shafer

Citations: 771 • 1988

CHOMP: Covariant Hamiltonian optimization for motion planning

Matt Zucker, Nathan Ratliff, Anca D. Dragan, Mihail Pivtoraiko, Matthew Klingensmith, Christopher M. Dellin, J. Andrew Bagnell, Siddhartha S Srinivasa

Citations: 738 • 2013

VFH+: reliable obstacle avoidance for fast mobile robots

Iwan Ulrich, J. Borenstein

Citations: 694 • 2002

Noise and the reality gap: The use of simulation in evolutionary robotics

Nick Jakobi, Phil Husbands, Inman Harvey

Citations: 618 • 1995

Real-time obstacle avoidance using harmonic potential functions

J.-O. Kim, P.K. Khosla

Citations: 564 • 2002

Obstacle avoidance in a dynamic environment: a collision cone approach

Animesh Chakravarthy, Debasish Ghose

Citations: 545 • 1998

Swarm of micro flying robots in the wild

Xin Zhou, Xiangyong Wen, Zhepei Wang, Yuman Gao, Haojia Li, Qianhao Wang, Tiankai Yang, Haojian Lu, Yanjun Cao, Chao Xu, Fei Gao

Citations: 539 • 2022

High-speed navigation using the global dynamic window approach

Oliver Brock, Oussama Khatib

Citations: 536 • 2003

The curvature-velocity method for local obstacle avoidance

Reid Simmons

Citations: 527 • 2002

Real-time obstacle avoidance using harmonic potential functions

J.-O. Kim, P.K. Khosla

Citations: 519 • 1992

Temporal logic motion planning for dynamic robots

Georgios Fainekos, Antoine Girard, Hadas Kress‐Gazit, George J. Pappas

Citations: 460 • 2008

Deep reinforcement learning based mobile robot navigation: A review

Kai Zhu, Tao Zhang

Citations: 458 • 2021