paper-with-me

Papers

Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks

2021-05-26 · Khadija Shaheen, Muhammad Abdullah Hanif, Osman Hasan, Muhammad Shafique

Continual learning is essential for all real-world applications, as frozen pre-trained models cannot effectively deal with non-stationary data distributions. The purpose of this study is to review the state-of-the-art methods that allow continuous learning of computational models over time. We primarily focus on the learning algorithms that perform continuous learning in an online fashion from considerably large (or infinite) sequential data and require substantially low computational and memory resources. We critically analyze the key challenges associated with continual learning for autonomous real-world systems and compare current methods in terms of computations, memory, and network/model complexity. We also briefly describe the implementations of continuous learning algorithms under three main autonomous systems, i.e., self-driving vehicles, unmanned aerial vehicles, and urban robots. The learning methods of these autonomous systems and their strengths and limitations are extensively explored in this article.

📄 PDF Abstract BibTeX arXiv:2105.12374

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Continual Learning with Neuromorphic Computing: Theories, Methods, and Applications

2024-10-11 · Mishal Fatima Minhas, Rachmad Vidya Wicaksana Putra, Falah Awwad, Osman Hasan 외

To adapt to real-world dynamics, intelligent systems need to assimilate new knowledge without catastrophic forgetting, where learning new tasks leads to a degradation in performance on old tasks. To address this, continu…

Continual Learning

Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges

2019-06-29 · Timothée Lesort, Vincenzo Lomonaco, Andrei Stoian, Davide Maltoni 외

Continual learning (CL) is a particular machine learning paradigm where the data distribution and learning objective changes through time, or where all the training data and objective criteria are never available at once…

BIG-bench Machine LearningContinual Learning

CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions

2020-09-14 · Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez, Massimo Caccia 외

In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous.…

BenchmarkingContinual Learning

Neuromorphic Computing for Embodied Intelligence in Autonomous Systems: Current Trends, Challenges, and Future Directions

2025-07-24 · Alberto Marchisio, Muhammad Shafique arxiv

The growing need for intelligent, adaptive, and energy-efficient autonomous systems across fields such as robotics, mobile agents (e.g., UAVs), and self-driving vehicles is driving interest in neuromorphic computing. By …

Continual Learning

Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback

2023-10-31 · Max Balsells, Marcel Torne, Zihan Wang, Samedh Desai 외

Ideally, we would place a robot in a real-world environment and leave it there improving on its own by gathering more experience autonomously. However, algorithms for autonomous robotic learning have been challenging to …

reinforcement-learningReinforcement LearningSelf-Supervised Learning