Local Planning

Local planning in robotics and reinforcement learning focuses on developing algorithms that enable agents to efficiently navigate complex environments and achieve goals by making localized decisions. Current research emphasizes improving sample efficiency through techniques like combining reinforcement learning with imitation learning, leveraging uncertainty-based exploration strategies, and employing advanced model architectures such as Soft Actor-Critic (SAC) and deep latent visual attention models. These advancements aim to create more robust and adaptable local planners, particularly for challenging scenarios like collision avoidance and heterogeneous terrain navigation, with significant implications for autonomous systems and real-world robotic applications.

Papers

June 26, 2024

Confident Natural Policy Gradient for Local Planning in $q_π$-realizable Constrained MDPs
Tian Tian, Lin F. Yang, Csaba Szepesvári
Policy Gradient Linear Function Approximation Reinforcement Learning Approach Constrained Markov Decision Process Local Planning

May 16, 2024

Combining RL and IL using a dynamic, performance-based modulation over learning signals and its application to local planning
Francisco Leiva, Javier Ruiz-del-Solar
Reinforcement Learning Imitation Learning Mobile Robot Reinforcement Learning Algorithm Behavior Cloning Abnormal Signal Modulation Scheme Local Planning

March 21, 2023

SACPlanner: Real-World Collision Avoidance with a Soft Actor Critic Local Planner and Polar State Representations
Khaled Nakhleh, Minahil Raza, Mack Tang, Matthew Andrews, Rinu Boney, Ilija Hadzic, Jeongran Lee, Atefeh Mohajeri, Karina Palyutina
Reinforcement Learning Collision Avoidance Real Robot Soft Actor Critic Polar Representation Local Planning

January 29, 2023

Sample Efficient Deep Reinforcement Learning via Local Planning
Dong Yin, Sridhar Thiagarajan, Nevena Lazic, Nived Rajaraman, Botao Hao, Csaba Szepesvari
Reinforcement Learning Uncertainty Aware Sample Efficient Reinforcement Learning Double DQN Local Planning Initial State Distribution

October 12, 2022

Local Planner Bench: Benchmarking for Local Motion Planning
Max Spahn, Chadi Salmi, Javier Alonso-Mora
Motion Planning Local Path Planning Custom Robot Local Motion Local Planning

December 9, 2021

Trajectory-Constrained Deep Latent Visual Attention for Improved Local Planning in Presence of Heterogeneous Terrain
Stefan Wapnick, Travis Manderson, David Meger, Gregory Dudek
Speech Presence Visual Attention Visual Navigation Task Convolutional Attention Heterogeneous Terrain Local Planning

Local Planning

Papers

Confident Natural Policy Gradient for Local Planning in $q_π$-realizable Constrained MDPs

Combining RL and IL using a dynamic, performance-based modulation over learning signals and its application to local planning

SACPlanner: Real-World Collision Avoidance with a Soft Actor Critic Local Planner and Polar State Representations

Sample Efficient Deep Reinforcement Learning via Local Planning

Local Planner Bench: Benchmarking for Local Motion Planning

Trajectory-Constrained Deep Latent Visual Attention for Improved Local Planning in Presence of Heterogeneous Terrain