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

  title={Safety, Challenges, and Performance of Motion Planners in Dynamic Environments},
  author={Hao-Tien Lewis Chiang and Baisravan Homchaudhuri and L. Smith and Lydia Tapia},
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… 

Chase and Track: Toward Safe and Smooth Trajectory Planning for Robotic Navigation in Dynamic Environments

A hierarchical planning framework with a global planner generating the shortest path between the robot and the navigation target and an event-triggered mechanism that executes the local plan aperiodically to release the computational burden is developed.

Real-time trajectory planning for automated vehicle safety and performance in dynamic environments

This paper presents a nonlinear model predictive control-based trajectory planning formulation, tailored for a large, high-speed unmanned ground vehicle, that includes the entire set of specifications, and indicates that the resulting formulation can be solved in real-time.

Search-Based Online Trajectory Planning for Car-like Robots in Highly Dynamic Environments

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.

Online State-Time Trajectory Planning Using Timed-ESDF in Highly Dynamic Environments

This work proposes a gradient-based planner on the state-time space for online trajectory generation in highly dynamic environments and proposes a Timed-ESDT that supports distance and gradient queries with state- time keys.

Learning Navigation Behaviors End to End

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.

Comparison of Deep Reinforcement Learning Policies to Formal Methods for Moving Obstacle Avoidance

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.

Robot Adaptation for Generating Consistent Navigational Behaviors over Unstructured Off-Road Terrain

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.

Towards Safe Navigation Through Crowded Dynamic Environments

  • Z. XiePujie XinP. Dames
  • Computer Science
    2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2021
This paper proposes a novel neural network-based control policy to enable a mobile robot to navigate safety through environments filled with both static obstacles, such as tables and chairs, and

NAUTS: Negotiation for Adaptation to Unstructured Terrain Surfaces

A novel approach for adaptation by negotiation that enables a ground robot to adjust its navigational behaviors through a negotiation process that outperforms previous methods for robot navigation, especially over unseen and uncertain dynamic terrains.

PEARL: PrEference Appraisal Reinforcement Learning for Motion Planning

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).



Stochastic Ensemble Simulation motion planning in stochastic dynamic environments

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.

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 the

Aggressive Moving Obstacle Avoidance Using a Stochastic Reachable Set Based Potential Field

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.

Path-guided artificial potential fields with stochastic reachable sets for motion planning in highly dynamic environments

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.

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. In

Hybrid Dynamic Moving Obstacle Avoidance Using a Stochastic Reachable Set-Based Potential Field

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.

Motion Planning in Dynamic Environments

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.

Real-Time Adaptive Motion Planning (RAMP) of Mobile Manipulators in Dynamic Environments With Unforeseen Changes

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.

A Survey of Motion Planning Algorithms from the Perspective of Autonomous UAV Guidance

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.

Detection of robustly collision-free trajectories in unpredictable environments in real-time

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.