Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight

• URL: http://arxiv.org/abs/2309.09865v3
• Date: Thu, 29 Feb 2024 10:43:39 GMT
• Title: Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight
• Authors: Jiaxu Xing, Leonard Bauersfeld, Yunlong Song, Chunwei Xing, Davide Scaramuzza
• Abstract summary: This work proposes an adaptive multi-pair contrastive learning strategy for visual representation learning that enables zero-shot scene transfer and real-world deployment. We demonstrate the performance of our approach on the task of agile, vision-based quadrotor flight.
• Score: 21.728935597793473
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scene transfer for vision-based mobile robotics applications is a highly relevant and challenging problem. The utility of a robot greatly depends on its ability to perform a task in the real world, outside of a well-controlled lab environment. Existing scene transfer end-to-end policy learning approaches often suffer from poor sample efficiency or limited generalization capabilities, making them unsuitable for mobile robotics applications. This work proposes an adaptive multi-pair contrastive learning strategy for visual representation learning that enables zero-shot scene transfer and real-world deployment. Control policies relying on the embedding are able to operate in unseen environments without the need for finetuning in the deployment environment. We demonstrate the performance of our approach on the task of agile, vision-based quadrotor flight. Extensive simulation and real-world experiments demonstrate that our approach successfully generalizes beyond the training domain and outperforms all baselines.

Related papers

• Flex: End-to-End Text-Instructed Visual Navigation with Foundation Models [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies. Our findings are synthesized in Flex (Fly-lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors. We demonstrate the effectiveness of this approach on quadrotor fly-to-target tasks, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• Learning and Adapting Agile Locomotion Skills by Transferring Experience [71.8926510772552]
  We propose a framework for training complex robotic skills by transferring experience from existing controllers to jumpstart learning new tasks. We show that our method enables learning complex agile jumping behaviors, navigating to goal locations while walking on hind legs, and adapting to new environments.
  arXiv  Detail & Related papers  (2023-04-19T17:37:54Z)
• An in-depth experimental study of sensor usage and visual reasoning of robots navigating in real environments [20.105395754497202]
  We study the performance and reasoning capacities of real physical agents, trained in simulation and deployed to two different physical environments. We show, that for the PointGoal task, an agent pre-trained on wide variety of tasks and fine-tuned on a simulated version of the target environment can reach competitive performance without modelling any sim2real transfer.
  arXiv  Detail & Related papers  (2021-11-29T16:27:29Z)
• Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation [26.47544415550067]
  We propose to distill a state-based motion planner augmented policy to a visual control policy. We evaluate our method on three manipulation tasks in obstructed environments. Our framework is highly sample-efficient and outperforms the state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2021-11-11T18:52:00Z)
• Towards Active Vision for Action Localization with Reactive Control and Predictive Learning [8.22379888383833]
  We formulate an energy-based mechanism that combines predictive learning and reactive control to perform active action localization without rewards. We demonstrate that the proposed approach can generalize to different tasks and environments in a streaming fashion, without explicit rewards or training.
  arXiv  Detail & Related papers  (2021-11-09T23:16:55Z)
• On Embodied Visual Navigation in Real Environments Through Habitat [20.630139085937586]
  Visual navigation models based on deep learning can learn effective policies when trained on large amounts of visual observations. To deal with this limitation, several simulation platforms have been proposed in order to train visual navigation policies on virtual environments efficiently. We show that our tool can effectively help to train and evaluate navigation policies on real-world observations without running navigation pisodes in the real world.
  arXiv  Detail & Related papers  (2020-10-26T09:19:07Z)
• Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments [20.017277077448924]
  NavACL is a method of automatic curriculum learning tailored to the navigation task. Deep reinforcement learning agents trained using NavACL significantly outperform state-of-the-art agents trained with uniform sampling. Our agents can navigate through unknown cluttered indoor environments to semantically-specified targets using only RGB images.
  arXiv  Detail & Related papers  (2020-09-11T13:28:26Z)
• ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation [99.2543521972137]
  ReLMoGen is a framework that combines a learned policy to predict subgoals and a motion generator to plan and execute the motion needed to reach these subgoals. Our method is benchmarked on a diverse set of seven robotics tasks in photo-realistic simulation environments. ReLMoGen shows outstanding transferability between different motion generators at test time, indicating a great potential to transfer to real robots.
  arXiv  Detail & Related papers  (2020-08-18T08:05:15Z)
• Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation [62.22058066456076]
  Reinforcement Learning (RL) represents powerful tools to solve complex robotic tasks. RL does not work directly in the real-world, which is known as the sim-to-real transfer problem. We propose a method that learns on an observation space constructed by point clouds and environment randomization.
  arXiv  Detail & Related papers  (2020-07-27T17:46:59Z)
• RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real [74.45688231140689]
  We introduce the RL-scene consistency loss for image translation, which ensures that the translation operation is invariant with respect to the Q-values associated with the image. We obtain RL-CycleGAN, a new approach for simulation-to-real-world transfer for reinforcement learning.
  arXiv  Detail & Related papers  (2020-06-16T08:58:07Z)
• Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning [109.77163932886413]
  We show how to adapt vision-based robotic manipulation policies to new variations by fine-tuning via off-policy reinforcement learning. This adaptation uses less than 0.2% of the data necessary to learn the task from scratch. We find that our approach of adapting pre-trained policies leads to substantial performance gains over the course of fine-tuning.
  arXiv  Detail & Related papers  (2020-04-21T17:57:04Z)

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.