One-4-All: Neural Potential Fields for Embodied Navigation
- URL: http://arxiv.org/abs/2303.04011v3
- Date: Sun, 30 Jul 2023 19:56:01 GMT
- Title: One-4-All: Neural Potential Fields for Embodied Navigation
- Authors: Sacha Morin, Miguel Saavedra-Ruiz, Liam Paull
- Abstract summary: Real-world navigation can require long-horizon planning using high-dimensional RGB images.
One-4-All (O4A) is a method leveraging self-supervised and manifold learning to obtain a graph-free, end-to-end navigation pipeline.
We show that O4A can reach long-range goals in 8 simulated Gibson indoor environments.
- Score: 10.452316044889177
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A fundamental task in robotics is to navigate between two locations. In
particular, real-world navigation can require long-horizon planning using
high-dimensional RGB images, which poses a substantial challenge for end-to-end
learning-based approaches. Current semi-parametric methods instead achieve
long-horizon navigation by combining learned modules with a topological memory
of the environment, often represented as a graph over previously collected
images. However, using these graphs in practice requires tuning a number of
pruning heuristics. These heuristics are necessary to avoid spurious edges,
limit runtime memory usage and maintain reasonably fast graph queries in large
environments. In this work, we present One-4-All (O4A), a method leveraging
self-supervised and manifold learning to obtain a graph-free, end-to-end
navigation pipeline in which the goal is specified as an image. Navigation is
achieved by greedily minimizing a potential function defined continuously over
image embeddings. Our system is trained offline on non-expert exploration
sequences of RGB data and controls, and does not require any depth or pose
measurements. We show that O4A can reach long-range goals in 8 simulated Gibson
indoor environments and that resulting embeddings are topologically similar to
ground truth maps, even if no pose is observed. We further demonstrate
successful real-world navigation using a Jackal UGV platform.
Related papers
- Feudal Networks for Visual Navigation [6.1190419149081245]
We introduce a new approach to visual navigation using feudal learning.
Agents at each level see a different aspect of the task and operate at different spatial and temporal scales.
The resulting feudal navigation network achieves near SOTA performance.
arXiv Detail & Related papers (2024-02-19T20:05:41Z) - Object Goal Navigation with Recursive Implicit Maps [92.6347010295396]
We propose an implicit spatial map for object goal navigation.
Our method significantly outperforms the state of the art on the challenging MP3D dataset.
We deploy our model on a real robot and achieve encouraging object goal navigation results in real scenes.
arXiv Detail & Related papers (2023-08-10T14:21:33Z) - How To Not Train Your Dragon: Training-free Embodied Object Goal
Navigation with Semantic Frontiers [94.46825166907831]
We present a training-free solution to tackle the object goal navigation problem in Embodied AI.
Our method builds a structured scene representation based on the classic visual simultaneous localization and mapping (V-SLAM) framework.
Our method propagates semantics on the scene graphs based on language priors and scene statistics to introduce semantic knowledge to the geometric frontiers.
arXiv Detail & Related papers (2023-05-26T13:38:33Z) - Learning to Predict Navigational Patterns from Partial Observations [63.04492958425066]
This paper presents the first self-supervised learning (SSL) method for learning to infer navigational patterns in real-world environments from partial observations only.
We demonstrate how to infer global navigational patterns by fitting a maximum likelihood graph to the DSLP field.
Experiments show that our SSL model outperforms two SOTA supervised lane graph prediction models on the nuScenes dataset.
arXiv Detail & Related papers (2023-04-26T02:08:46Z) - ReVoLT: Relational Reasoning and Voronoi Local Graph Planning for
Target-driven Navigation [1.0896567381206714]
Embodied AI is an inevitable trend that emphasizes the interaction between intelligent entities and the real world.
Recent works focus on exploiting layout relationships by graph neural networks (GNNs)
We decouple this task and propose ReVoLT, a hierarchical framework.
arXiv Detail & Related papers (2023-01-06T05:19:56Z) - ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints [94.60414567852536]
Long-range navigation requires both planning and reasoning about local traversability.
We propose a learning-based approach that integrates learning and planning.
ViKiNG can leverage its image-based learned controller and goal-directed to navigate to goals up to 3 kilometers away.
arXiv Detail & Related papers (2022-02-23T02:14:23Z) - Lifelong Topological Visual Navigation [16.41858724205884]
We propose a learning-based visual navigation method with graph update strategies that improve lifelong navigation performance over time.
We take inspiration from sampling-based planning algorithms to build image-based topological graphs, resulting in sparser graphs yet with higher navigation performance compared to baseline methods.
Unlike controllers that learn from fixed training environments, we show that our model can be finetuned using a relatively small dataset from the real-world environment where the robot is deployed.
arXiv Detail & Related papers (2021-10-16T06:16:14Z) - Memory-Augmented Reinforcement Learning for Image-Goal Navigation [67.3963444878746]
We present a novel method that leverages a cross-episode memory to learn to navigate.
In order to avoid overfitting, we propose to use data augmentation on the RGB input during training.
We obtain this competitive performance from RGB input only, without access to additional sensors such as position or depth.
arXiv Detail & Related papers (2021-01-13T16:30:20Z) - Learning Synthetic to Real Transfer for Localization and Navigational
Tasks [7.019683407682642]
Navigation is at the crossroad of multiple disciplines, it combines notions of computer vision, robotics and control.
This work aimed at creating, in a simulation, a navigation pipeline whose transfer to the real world could be done with as few efforts as possible.
To design the navigation pipeline four main challenges arise; environment, localization, navigation and planning.
arXiv Detail & Related papers (2020-11-20T08:37:03Z) - Occupancy Anticipation for Efficient Exploration and Navigation [97.17517060585875]
We propose occupancy anticipation, where the agent uses its egocentric RGB-D observations to infer the occupancy state beyond the visible regions.
By exploiting context in both the egocentric views and top-down maps our model successfully anticipates a broader map of the environment.
Our approach is the winning entry in the 2020 Habitat PointNav Challenge.
arXiv Detail & Related papers (2020-08-21T03:16:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.