mlsanityData to 7 Oct 2026

Towards self-attention based visual navigation in the real world

arXiv 2209.07043 ↗First posted 15 Sep 2022cs.RO cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Vision guided navigation requires processing complex visual information to inform task-orientated decisions. Applications include autonomous robots, self-driving cars, and assistive vision for humans. A key element is the extraction and selection of relevant features in pixel space upon which to base action choices, for which Machine Learning techniques are well suited. However, Deep Reinforcement Learning agents trained in simulation often exhibit unsatisfactory results when deployed in the real-world due to perceptual differences known as the textitreality gap. An approach that is yet to be explored to bridge this gap is self-attention. In this paper we (1) perform a systematic exploration of the hyperparameter space for self-attention based navigation of 3D environments and qualitatively appraise behaviour observed from different hyperparameter sets, including their ability to generalise; (2) present strategies to improve the agents' generalisation abilities and navigation behaviour; and (3) show how models trained in simulation are capable of processing real world images meaningfully in real time. To our knowledge, this is the first demonstration of a self-attention based agent successfully trained in navigating a 3D action space, using less than 4000 parameters.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 33 references that are in the map. First posted on arXiv 15 Sep 2022.

Builds on

18 of 33 references.

References · 18

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2015Trust Region Policy Optimizationcited by 2,503
  3. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  4. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  5. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  6. 2016The CMA Evolution Strategy: A Tutorialcited by 364
  7. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 292
  8. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 138
  9. 2019Towards Interpretable Reinforcement Learning Using Attention Augmented Agentscited by 82
  10. 2020Neuroevolution of Self-Interpretable Agentscited by 48
  11. 2018VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Controlcited by 34
  12. 2019SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigationcited by 29
6 more
  1. 2018A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policiescited by 10
  2. 2017Teaching a Machine to Read Maps with Deep Reinforcement Learningcited by 9
  3. 2017GeneSIS-RT: Generating Synthetic Images for training Secondary Real-world Taskscited by 5
  4. 2019Using RGB Image as Visual Input for Mapless Robot Navigationcited by 5
  5. 2013Generative NeuroEvolution for Deep Learningcited by 2
  6. 2018Attend Before you Act: Leveraging human visual attention for continual learningcited by 2

Built on by

Not cited yet.