• Corpus ID: 231839682

An advantage actor-critic algorithm for robotic motion planning in dense and dynamic scenarios

@article{Zhou2021AnAA,
  title={An advantage actor-critic algorithm for robotic motion planning in dense and dynamic scenarios},
  author={Chengmin Zhou and Bingding Huang and Pasi Fr{\"a}nti},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.03138}
}
Intelligent robots provide a new insight into efficiency improvement in industrial and service scenarios to replace human labor. However, these scenarios include dense and dynamic obstacles that make motion planning of robots challenging. Traditional algorithms like A* can plan collision-free trajectories in static environment, but their performance degrades and computational cost increases steeply in dense and dynamic scenarios. Optimal-value reinforcement learning algorithms (RL) can address… 
1 Citations

Figures and Tables from this paper

Distributed Optimization for Distribution Grids With Stochastic DER Using Multi-Agent Deep Reinforcement Learning

A special decomposition methodology for the traditional optimal power flow which facilitates optimal integration of stochastic distributed energy resources in power distribution systems and accelerates conventional linear programming approach by considering a reduced set of resources and their constraints.

References

SHOWING 1-10 OF 26 REFERENCES

Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning

This work extends the previous approach to develop an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules, and introduces a strategy using LSTM that enables the algorithm to use observations of an arbitrary number of other agents, instead of previous methods that have a fixed observation size.

Rapidly-exploring Random Belief Trees for motion planning under uncertainty

  • A. BryN. Roy
  • Mathematics
    2011 IEEE International Conference on Robotics and Automation
  • 2011
The algorithm incrementally constructs a graph of trajectories through state space, while efficiently searching over candidate paths through the graph at each iteration results in a search tree in belief space that provably converges to the optimal path.

Continuous control with deep reinforcement learning

This work presents an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces, and demonstrates that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs.

Socially aware motion planning with deep reinforcement learning

Using deep reinforcement learning, this work develops a time-efficient navigation policy that respects common social norms and is shown to enable fully autonomous navigation of a robotic vehicle moving at human walking speed in an environment with many pedestrians.

Reciprocal Velocity Obstacles for real-time multi-agent navigation

This paper applies the "Reciprocal Velocity Obstacle" concept to navigation of hundreds of agents in densely populated environments containing both static and moving obstacles, and shows that real-time and scalable performance is achieved in such challenging scenarios.

ClearPath: highly parallel collision avoidance for multi-agent simulation

The approach extends the notion of velocity obstacles from robotics and formulates the conditions for collision free navigation as a quadratic optimization problem and uses a discrete optimization method to efficiently compute the motion of each agent.

Reinforcement Learning: An Introduction

This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.

Policy Gradient Methods for Reinforcement Learning with Function Approximation

This paper proves for the first time that a version of policy iteration with arbitrary differentiable function approximation is convergent to a locally optimal policy.

Deep Q-learning From Demonstrations

This paper presents an algorithm, Deep Q-learning from Demonstrations (DQfD), that leverages small sets of demonstration data to massively accelerate the learning process even from relatively small amounts of demonstrating data and is able to automatically assess the necessary ratio of demonstrationData while learning thanks to a prioritized replay mechanism.

Crowd-Robot Interaction: Crowd-Aware Robot Navigation With Attention-Based Deep Reinforcement Learning

This work proposes to rethink pairwise interactions with a self-attention mechanism, and jointly model Human-Robot as well as Human-Human interactions in the deep reinforcement learning framework, and captures the Human- human interactions occurring in dense crowds that indirectly affects the robot’s anticipation capability.