Learning 3D Robotics Perception using Inductive Priors
Muhammad Zubair Irshad

TL;DR
This paper explores how incorporating structured prior knowledge into deep learning models enhances 3D perception in robotics, enabling better generalization with less real-world data through various priors and transfer learning techniques.
Contribution
It introduces methods to encode diverse priors into deep learning models for 3D robotics perception, improving generalization and reducing dependence on large labeled datasets.
Findings
Prior knowledge improves 3D reconstruction accuracy.
Structured priors enable effective transfer learning.
Models generalize better to unseen environments.
Abstract
Recent advances in deep learning have led to a data-centric intelligence i.e. artificially intelligent models unlocking the potential to ingest a large amount of data and be really good at performing digital tasks such as text-to-image generation, machine-human conversation, and image recognition. This thesis covers the topic of learning with structured inductive bias and priors to design approaches and algorithms unlocking the potential of principle-centric intelligence. Prior knowledge (priors for short), often available in terms of past experience as well as assumptions of how the world works, helps the autonomous agent generalize better and adapt their behavior based on past experience. In this thesis, I demonstrate the use of prior knowledge in three different robotics perception problems. 1. object-centric 3D reconstruction, 2. vision and language for decision-making, and 3. 3D…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Algorithms · Robot Manipulation and Learning · Robotics and Sensor-Based Localization
