Robust Monocular Visual Odometry using Curriculum Learning
- URL: http://arxiv.org/abs/2411.13438v1
- Date: Wed, 20 Nov 2024 16:26:51 GMT
- Title: Robust Monocular Visual Odometry using Curriculum Learning
- Authors: Assaf Lahiany, Oren Gal,
- Abstract summary: Our work applies innovative Curriculum Learning (CL) methodologies to address the challenging geometric problem of monocular Visual Odometry (VO) estimation.
We enhance the end-to-end Deep-Patch-Visual Odometry framework through the integration of novel CL approaches.
- Score: 1.282543877006303
- License:
- Abstract: Curriculum Learning (CL), drawing inspiration from natural learning patterns observed in humans and animals, employs a systematic approach of gradually introducing increasingly complex training data during model development. Our work applies innovative CL methodologies to address the challenging geometric problem of monocular Visual Odometry (VO) estimation, which is essential for robot navigation in constrained environments. The primary objective of our research is to push the boundaries of current state-of-the-art (SOTA) benchmarks in monocular VO by investigating various curriculum learning strategies. We enhance the end-to-end Deep-Patch-Visual Odometry (DPVO) framework through the integration of novel CL approaches, with the goal of developing more resilient models capable of maintaining high performance across challenging environments and complex motion scenarios. Our research encompasses several distinctive CL strategies. We develop methods to evaluate sample difficulty based on trajectory motion characteristics, implement sophisticated adaptive scheduling through self-paced weighted loss mechanisms, and utilize reinforcement learning agents for dynamic adjustment of training emphasis. Through comprehensive evaluation on the real-world TartanAir dataset, our Curriculum Learning-based Deep-Patch-Visual Odometry (CL-DPVO) demonstrates superior performance compared to existing SOTA methods, including both feature-based and learning-based VO approaches. The results validate the effectiveness of integrating curriculum learning principles into visual odometry systems.
Related papers
- Reward-free World Models for Online Imitation Learning [25.304836126280424]
We propose a novel approach to online imitation learning that leverages reward-free world models.
Our method learns environmental dynamics entirely in latent spaces without reconstruction, enabling efficient and accurate modeling.
We evaluate our method on a diverse set of benchmarks, including DMControl, MyoSuite, and ManiSkill2, demonstrating superior empirical performance compared to existing approaches.
arXiv Detail & Related papers (2024-10-17T23:13:32Z) - Contrastive-Adversarial and Diffusion: Exploring pre-training and fine-tuning strategies for sulcal identification [3.0398616939692777]
Techniques like adversarial learning, contrastive learning, diffusion denoising learning, and ordinary reconstruction learning have become standard.
The study aims to elucidate the advantages of pre-training techniques and fine-tuning strategies to enhance the learning process of neural networks.
arXiv Detail & Related papers (2024-05-29T15:44:51Z) - Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decomposition [5.01338577379149]
Continual learning (CL) has spurred the development of several methods aimed at consolidating previous knowledge across sequential learning.
We propose a novel representation-based evaluation framework for CL models.
arXiv Detail & Related papers (2024-05-06T07:52:44Z) - Dynamic Sub-graph Distillation for Robust Semi-supervised Continual
Learning [52.046037471678005]
We focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories.
We propose a novel approach called Dynamic Sub-Graph Distillation (DSGD) for semi-supervised continual learning.
arXiv Detail & Related papers (2023-12-27T04:40:12Z) - Learning Objective-Specific Active Learning Strategies with Attentive
Neural Processes [72.75421975804132]
Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting.
We propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem.
Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives.
arXiv Detail & Related papers (2023-09-11T14:16:37Z) - ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
We introduce Action-Aware Embodied Learning for Perception (ALP)
ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective.
We show that ALP outperforms existing baselines in several downstream perception tasks.
arXiv Detail & Related papers (2023-06-16T21:51:04Z) - Predictive Experience Replay for Continual Visual Control and
Forecasting [62.06183102362871]
We present a new continual learning approach for visual dynamics modeling and explore its efficacy in visual control and forecasting.
We first propose the mixture world model that learns task-specific dynamics priors with a mixture of Gaussians, and then introduce a new training strategy to overcome catastrophic forgetting.
Our model remarkably outperforms the naive combinations of existing continual learning and visual RL algorithms on DeepMind Control and Meta-World benchmarks with continual visual control tasks.
arXiv Detail & Related papers (2023-03-12T05:08:03Z) - Latent Variable Representation for Reinforcement Learning [131.03944557979725]
It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning.
We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle.
In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
arXiv Detail & Related papers (2022-12-17T00:26:31Z) - Robust Visual Odometry Using Position-Aware Flow and Geometric Bundle
Adjustment [16.04240592057438]
A novel optical flow network (PANet) built on a position-aware mechanism is proposed first.
Then, a novel system that jointly estimates depth, optical flow, and ego-motion without a typical network to learning ego-motion is proposed.
Experiments show that the proposed system not only outperforms other state-of-the-art methods in terms of depth, flow, and VO estimation.
arXiv Detail & Related papers (2021-11-22T12:05:27Z) - Learning Multi-Objective Curricula for Deep Reinforcement Learning [55.27879754113767]
Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL)
In this paper, we propose a unified automatic curriculum learning framework to create multi-objective but coherent curricula.
In addition to existing hand-designed curricula paradigms, we further design a flexible memory mechanism to learn an abstract curriculum.
arXiv Detail & Related papers (2021-10-06T19:30:25Z)
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.