RECORD
SACPlanner: Real-World Collision Avoidance with a Soft Actor Critic Local Planner and Polar State Representations
Robotics · Submitted 21 Mar 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We also observe that on real-world robots the resulting SACPlanner is more reactive to obstacles than traditional ROS local planners such as DWA.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
We study the training performance of ROS local planners based on Reinforcement Learning (RL), and the trajectories they produce on real-world robots. We show that recent enhancements to the Soft Actor Critic (SAC) algorithm such as RAD and DrQ achieve almost perfect training after only 10000 episodes. We also observe that on real-world robots the resulting SACPlanner is more reactive to obstacles than traditional ROS local planners such as DWA.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | We study the training performance of ROS local planners based on Reinforcement Learning (RL), and the trajectories they produce on real-world robots. | contribution 0.90 | 0.84 | 0.05 | asserted 0.51 |
| s1 | We show that recent enhancements to the Soft Actor Critic (SAC) algorithm such as RAD and DrQ achieve almost perfect training after only 10000 episodes. | result 1.00 | 0.81 | 0.17 | asserted 1.00 |
| s2 | We also observe that on real-world robots the resulting SACPlanner is more reactive to obstacles than traditional ROS local planners such as DWA. | result 1.00 | 0.94 | 0.47 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
We study the training performance of ROS local planners based on Reinforcement Learning (RL), and the trajectories they produce on real-world robots. We show that recent enhancements to the Soft Actor Critic (SAC) algorithm such as RAD and DrQ achieve almost perfect training after only 10000 episodes. We also observe that on real-world robots the resulting SACPlanner is more reactive to obstacles than traditional ROS local planners such as DWA.
Human review
How the literature uses it
1 arXiv paper cite this in 1 sentence
What it cites · 4 sentences without a confident label
Uses the method or tool of 3 papers
-
In this work, we use a state-of-the-art off-policy actor-critic algorithm called Soft Actor-Critic (SAC) [ref] .
Soft Actor-Critic Algorithms and Applications · Soft Actor Critic Algorithm · 0.99
-
In this work, we consider the recently proposed RAD [ref] and DrQ [ref] methods that apply image augmentations for sample-efficient learning of continuous control policies from image observations.
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels · Soft Actor Critic Algorithm · 0.98
-
Following previous works [ref] , we train the convolutional encoder network using only the critic loss and then detach the network parameters from the actor loss for improved training stability.
CURL: Contrastive Unsupervised Representations for Reinforcement Learning · Soft Actor Critic Algorithm · 0.92
Cites as background 1 paper
-
One notable success of Deep RL is in learning policies for game environments (e.g. Atari games) modeled as Markov Decision Processes (MDPs) and standardized as OpenAI Gym environments [ref] .
Playing Atari with Deep Reinforcement Learning · Introduction · 0.86
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.