Help Me Through: Imitation Learning Based Active View Planning to Avoid SLAM Tracking Failures

Large-scale evaluation of state-of-the-art visual SLAM has shown that its tracking performance degrades considerably if the camera view is not adjusted to avoid the low-texture areas. Deep reinforcement learning based approaches have been proposed to improve the robustness of visual tracking in such unsupervised settings. Our extensive analysis reveals the fundamental limitations of reinforcement learning based active view planning, especially in transition scenarios (entering/exiting the room, texture-less walls, and lobbies). In challenging transition scenarios, the agent generally remains unable to cross the transition during training, limiting its ability to learn the maneuver. We propose human-supervised RL training (imitation learning) and achieve significantly improved performance after <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 50 hours of supervised training. To reduce longer human supervision requirements, we also explore fine-tuning our network with an online learning policy. Here, we use limited human-supervised training (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 20 hours), and fine-tune the network with unsupervised training (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 45 hours), obtaining encouraging results. We also release our multi-model, human supervised training dataset. The dataset contains challenging and diverse transition scenarios and can aid the development of imitation learning policies for consistent visual tracking. We also release our implementation <xref ref-type="fn" rid="fn1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">¹</xref><fn id="fn1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><label>¹</label> <uri>https://tinyurl.com/478maz6u</uri> </fn>.