Safety, Challenges, and Performance of Motion Planners in Dynamic Environments

@inproceedings{Chiang2017SafetyCA,
  title={Safety, Challenges, and Performance of Motion Planners in Dynamic Environments},
  author={Hao-Tien Lewis Chiang and Baisravan Homchaudhuri and Lee Smith and Lydia Tapia},
  booktitle={ISRR},
  year={2017}
}
Providing safety guarantees for autonomous vehicle navigation is an ultimate goal for motion planning in dynamic environments. However, due to factors such as robot and obstacle dynamics, e.g., speed and nonlinearity, obstacle motion uncertainties, and a large number of moving obstacles, identifying complete motion planning solutions with collision-free safety guarantees is practically unachievable. Since complete motion planning solutions are intractable, it is critical to explore the factors… Expand
Search-Based Online Trajectory Planning for Car-like Robots in Highly Dynamic Environments
TLDR
A search-based partial motion planner for generating feasible trajectories of car-like robots in highly dynamic environments that can effectively explore the state-time space to generate near-time-optimal solutions. Expand
Online State-Time Trajectory Planning Using Timed-ESDF in Highly Dynamic Environments
TLDR
Experimental results on simulated and benchmark datasets show that the proposed gradient-based planner can outperform the state-of-the-art methods, demonstrating its significant advantages over the traditional ones. Expand
Learning Navigation Behaviors End to End
TLDR
Over 500 meters of on-robot experiments show these policies generalize to new environments and moving obstacles, are robust to sensor, actuator, and localization noise, and can serve as robust building blocks for larger navigation tasks. Expand
Comparison of Deep Reinforcement Learning Policies to Formal Methods for Moving Obstacle Avoidance
TLDR
The expected cumulative reward and actions of deep Reinforcement Learning policies are compared to stochastic reachability, and it is found that the state-value function approximates the optimal collision probability well, thus explaining the high empirical performance. Expand
Robot Adaptation for Generating Consistent Navigational Behaviors over Unstructured Off-Road Terrain
TLDR
Experimental results have validated that the proposed novel approach for consistent behavior generation enables robots to traverse complex unstructured off-road terrain with more navigational behavior consistency, and it outperforms previous methods, particularly so on challenging terrain. Expand
PEARL: PrEference Appraisal Reinforcement Learning for Motion Planning
TLDR
PEARL uses reinforcement learning on a restricted training domain, combined with features engineered from user-given intents, to propose a motion planning solution, PrEference Appraisal Reinforcement Learning (PEARL). Expand
Reactive Navigation in Crowds for Non-Holonomic Robots With Convex Bounding Shape
TLDR
A novel method for non-holonomic robots of convex shape to avoid imminent collisions with moving obstacles by correcting steering from the robot's path planner or driver is described. Expand
Develop the socially human-aware navigation system using dynamic window approach and optimize cost function for autonomous medical robot
TLDR
A novel framework of human’s zones to ensure safety for social interactions in human-machine system is proposed and are useful for robot’'s navigation in presence of human while the socially comfortable interaction is guaranteed. Expand
Learning Navigation Behaviors End-to-End With AutoRL
TLDR
Empirical evaluations show that AutoRL policies do not suffer from the catastrophic forgetfulness that plagues many other deep reinforcement learning algorithms, generalize to new environments and moving obstacles, are robust to sensor, actuator, and localization noise, and can serve as robust building blocks for larger navigation tasks. Expand
Defensive Escort Teams for Navigation in Crowds via Multi-Agent Deep Reinforcement Learning
TLDR
This letter presents a novel, end-to-end solution for coordinating an escort team for protecting high-value payloads in a space crowded with interacting obstacles and employs deep reinforcement learning in order to train a team of escorts to maintain payload safety while navigating alongside the payload. Expand
...
1
2
...

References

SHOWING 1-10 OF 40 REFERENCES
Stochastic Ensemble Simulation motion planning in stochastic dynamic environments
TLDR
The experiments show SES-based planning outperforms other methods that have high planning success in environments with 900 stochastically moving obstacles and plans trajectories with an 80% success rate for a 7 DOF robot in an environment with 250 stochasticMoving obstacles and 50 obstacles with speed/position uncertainty. Expand
Motion Planning in Dynamic Environments Using Velocity Obstacles
This paper presents a method for robot motion planning in dynamic environments. It consists of selecting avoidance maneuvers to avoid static and moving obstacles in the velocity space, based on theExpand
Aggressive Moving Obstacle Avoidance Using a Stochastic Reachable Set Based Potential Field
TLDR
This paper proposes a method to integrate formal SR sets with ad-hoc APFs for multiple moving obstacles, reaching over 86 % success in an enclosed space with 100 moving obstacles that ricochet off the walls. Expand
Path-guided artificial potential fields with stochastic reachable sets for motion planning in highly dynamic environments
TLDR
This paper proposes a novel technique that provides computationally efficient planning solutions in environments with static obstacles and several dynamic obstacles with stochastic motions, and shows that Path-Guided APF-SR outperforms other methods that have high planning success invironments with 300 stochastically moving obstacles. Expand
A review on motion planning and obstacle avoidance approaches in dynamic environments
Path planning with obstacles avoidance in dynamic environments is a crucial issue in robotics. Numerous approaches have been suggested for the navigation of mobile robots with moving obstacles. InExpand
Hybrid Dynamic Moving Obstacle Avoidance Using a Stochastic Reachable Set-Based Potential Field
TLDR
This work utilizes the APF framework for runtime planning but uses a formal validation method, Stochastic Reachable (SR) sets, to generate accurate potential fields for moving obstacles to outperforms the traditional Gaussian APF method. Expand
Motion Planning in Dynamic Environments
TLDR
This study of robot motion planning in dynamic domains presents algorithms for generating motion in an environment that changes over time and can serve as a reference for those working on spatial reasoning and autonomous robotic systems. Expand
Real-Time Adaptive Motion Planning (RAMP) of Mobile Manipulators in Dynamic Environments With Unforeseen Changes
TLDR
The results show that the RAMP planner, with its high efficiency and flexibility, not only handles a single mobile manipulator well in dynamic environments with various obstacles of unknown motions in addition to static obstacles, but can also readily and effectively plan motions for eachMobile manipulator in an environment shared by multiple mobile manipulators and other moving obstacles. Expand
A Survey of Motion Planning Algorithms from the Perspective of Autonomous UAV Guidance
TLDR
The purpose of this paper is to provide an overview of existing motion planning algorithms while adding perspectives and practical examples from UAV guidance approaches. Expand
Detection of robustly collision-free trajectories in unpredictable environments in real-time
TLDR
This paper introduces a general approach to detect if a high-DOF robot trajectory is continuously collision-free even in the presence of robot motion uncertainty in an unpredictable environment in real time, based on the novel concept of dynamic envelope. Expand
...
1
2
3
4
...