Improving Reliable Navigation under Uncertainty via Predictions Informed by Non-Local Information
Not on the map. Why?
Abstract (arXiv)
We improve reliable, long-horizon, goal-directed navigation in partially-mapped environments by using non-locally available information to predict the goodness of temporally-extended actions that enter unseen space. Making predictions about where to navigate in general requires non-local information: any observations the robot has seen so far may provide information about the goodness of a particular direction of travel. Building on recent work in learning-augmented model-based planning under uncertainty, we present an approach that can both rely on non-local information to make predictions (via a graph neural network) and is reliable by design: it will always reach its goal, even when learning does not provide accurate predictions. We conduct experiments in three simulated environments in which non-local information is needed to perform well. In our large scale university building environment, generated from real-world floorplans to the scale, we demonstrate a 9.3% reduction in cost-to-go compared to a non-learned baseline and a 14.9% reduction compared to a learning-informed planner that can only use local information to inform its predictions.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 40 references that are in the map. First posted on arXiv 26 Jul 2023.
Builds on
26 of 40 references.
References · 26
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
- 2021How Attentive are Graph Attention Networks?cited by 818
- 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
- 2017Deep Reinforcement Learning that Matterscited by 727
- 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
- 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
- 2017Cognitive Mapping and Planning for Visual Navigationcited by 209
- 2016Learning to Navigate in Complex Environmentscited by 192
- 2021SOON: Scenario Oriented Object Navigation with Graph-based Explorationcited by 118
14 more
- 2018Learning to Navigate in Cities Without a Mapcited by 103
- 2017Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigationcited by 90
- 2018Unsupervised Predictive Memory in a Goal-Directed Agentcited by 54
- 2016Deep Reinforcement Learning with Successor Features for Navigation across Similar Environmentscited by 50
- 2019Structured Object-Aware Physics Prediction for Video Modeling and Planningcited by 42
- 2016From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robotscited by 37
- 2020Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphscited by 23
- 2020Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planningcited by 19
- 2020Semantic and Geometric Modeling with Neural Message Passing in 3D Scene Graphs for Hierarchical Mechanical Searchcited by 14
- 2022Representation, learning, and planning algorithms for geometric task and motion planningcited by 8
- 2021Program Synthesis Guided Reinforcement Learning for Partially Observed Environmentscited by 7
- 2021Learning and Planning for Temporally Extended Tasks in Unknown Environmentscited by 7
- 2021Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertaintycited by 6
- 2020Graph-Based Generative Representation Learning of Semantically and Behaviorally Augmented Floorplanscited by 4
Built on by
Not cited yet.