Real-time reciprocal collision avoidance with elliptical agents

Best, Andrew; Narang, Sahil; Manocha, Dinesh

doi:10.1109/icra.2016.7487148

Cited by 51 publications

(36 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When walking in dense crowds, pedestrians keep changing their velocities frequently to avoid collisions with other pedestrians. Pedestrians also exhibit local interactions and other collision-avoidance behaviors such as side-stepping, shoulder-turning, and backpedaling [35]. As a result, prior motion models with constant velocity or constant acceleration assumptions do not accurately model crowded scenarios.…”

Section: Frvo: Local Trajectory Predictionmentioning

confidence: 99%

“…In practice, computing the exact Minkowski sums of ellipses is much more expensive as compared to those of circles. To overcome the complexity of exact Minkowski Sum computation, we compute conservative linear approximations of ellipses [35] and represent them as convex polygons. As a result, the collision avoidance problem reduces to linear programming.…”

Section: Computing Predicted Velocitiesmentioning

confidence: 99%

See 1 more Smart Citation

DensePeds: Pedestrian Tracking in Dense Crowds Using Front-RVO and Sparse Features

Chandra

Bhattacharya

Bera³

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

We present a pedestrian tracking algorithm, DensePeds, that tracks individuals in highly dense crowds (>2 pedestrians per square meter). Our approach is designed for videos captured from front-facing or elevated cameras. We present a new motion model called Front-RVO (FRVO) for predicting pedestrian movements in dense situations using collision avoidance constraints and combine it with state-of-theart Mask R-CNN to compute sparse feature vectors that reduce the loss of pedestrian tracks (false negatives). We evaluate DensePeds on the standard MOT benchmarks as well as a new dense crowd dataset. In practice, our approach is 4.5× faster than prior tracking algorithms on the MOT benchmark and we are state-of-the-art in dense crowd videos by over 2.6% on the absolute scale on average.

show abstract

Section: Frvo: Local Trajectory Predictionmentioning

confidence: 99%

Section: Computing Predicted Velocitiesmentioning

confidence: 99%

DensePeds: Pedestrian Tracking in Dense Crowds Using Front-RVO and Sparse Features

Chandra

Bhattacharya

Bera³

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Robot initial position is set to (5,10), and it has to move towards a goal at (20,20). Several circular obstacles representing passive agents are randomly distributed in a square region bounded by (0, 0) and (22,22).…”

Section: Collision Avoidance With Multiple Passive Agentsmentioning

confidence: 99%

“…Instead of complete motion planning, their approach was to plan local motion directed towards the next (sub) goal extracted from a global way point plan. Several efforts have been made to extend the concept of ORCA to more complex dynamic systems ranging from the single integrator, differential driven, car-like robot and arbitrary linear equation of motion in [20][21][22][23][24][25]. However, these approaches require every agent in a collision to run a similar collision avoidance algorithm.…”

Section: Introductionmentioning

confidence: 99%

Collision Avoidance from Multiple Passive Agents with Partially Predictable Behavior

et al. 2017

View full text Add to dashboard Cite

Navigating a robot in a dynamic environment is a challenging task, especially when the behavior of other agents such as pedestrians, is only partially predictable. Also, the kinodynamic constraints on robot motion add an extra challenge. This paper proposes a novel navigational strategy for collision avoidance of a kinodynamically constrained robot from multiple moving passive agents with partially predictable behavior. Specifically, this paper presents a new approach to identify the set of control inputs to the robot, named control obstacle, which leads it towards a collision with a passive agent moving along an arbitrary path. The proposed method is developed by generalizing the concept of nonlinear velocity obstacle (NLVO), which is used to avoid collision with a passive agent, and takes into account the kinodynamic constraints on robot motion. Further, it formulates the navigational problem as an optimization problem, which allows the robot to make a safe decision in the presence of various sources of unmodelled uncertainties. Finally, the performance of the algorithm is evaluated for different parameters and is compared to existing velocity obstacle-based approaches. The simulated experiments show the excellent performance of the proposed approach in term of computation time and success rate.

show abstract

“…ORCA provides an efficient way for computing a collision-free velocity outside the union of all VOs by conservatively approximating each VO as a half-plane and using linear programming to quickly find a feasible solution. As ORCA can also provide formal guarantees about the collision-free behavior of the agents, it has become very popular and many variants have been proposed based on modified VO formulations, including approaches for non-holonomic and car-like robots [2,3], as well as elliptical agents [8] to name just a few.…”

Section: Introductionmentioning

confidence: 99%

Uncertainty Models for TTC-Based Collision-Avoidance

Forootaninia

Karamouzas

Narain

2017

Robotics: Science and Systems XIII

View full text Add to dashboard Cite

Abstract-We address the problem of uncertainty-aware local collision avoidance within the context of time-to-collision based navigation of multiple agents. We consider two specific models that account for uncertainty in the future trajectories of interacting agents: an isotropic model which conservatively considers all possible errors, and an adversarial model that assumes the error is towards a head-on collision. We compare the two models experimentally via a number of simulation scenarios, and also provide theoretical guarantees about the collision avoidance behavior of the agents.

show abstract

Real-time reciprocal collision avoidance with elliptical agents

Cited by 51 publications

References 26 publications

DensePeds: Pedestrian Tracking in Dense Crowds Using Front-RVO and Sparse Features

DensePeds: Pedestrian Tracking in Dense Crowds Using Front-RVO and Sparse Features

Collision Avoidance from Multiple Passive Agents with Partially Predictable Behavior

Uncertainty Models for TTC-Based Collision-Avoidance

Contact Info

Product

Resources

About