Robust active binocular vision through intrinsically motivated learning

Abstract

The efficient coding hypothesis posits that sensory systems of animals strive to encode sensory signals efficiently by taking into account the redundancies in them. This principle has been very successful in explaining response properties of visual sensory neurons as adaptations to the statistics of natural images. Recently, we have begun to extend the efficient coding hypothesis to active perception through a form of intrinsically motivated learning: a sensory model learns an efficient code for the sensory signals while a reinforcement learner generates movements of the sense organs to improve the encoding of the signals. To this end, it receives an intrinsically generated reinforcement signal indicating how well the sensory model encodes the data. This approach has been tested in the context of binocular vison, leading to the autonomous development of disparity tuning and vergence control. Here we systematically investigate the robustness of the new approach in the context of a binocular vision system implemented on a robot. Robustness is an important aspect that reflects the ability of the system to deal with unmodeled disturbances or events, such as insults to the system that displace the stereo cameras. To demonstrate the robustness of our method and its ability to self-calibrate, we introduce various perturbations and test if and how the system recovers from them. We find that (1) the system can fully recover from a perturbation that can be compensated through the system's motor degrees of freedom, (2) performance degrades gracefully if the system cannot use its motor degrees of freedom to compensate for the perturbation, and (3) recovery from a perturbation is improved if both the sensory encoding and the behavior policy can adapt to the perturbation. Overall, this work demonstrates that our intrinsically motivated learning approach for efficient coding in active perception gives rise to a self-calibrating perceptual system of high robustness.

Curiosity‐based learning in infants: a neurocomputational approach

“…In contrast to the relative scarcity of research into infant curiosity, recent years have seen a surge in interest in the role of intrinsic motivation in autonomous computational systems. Equipping artificial learning systems with intrinsic motivation mechanisms is likely to be key to building autonomously intelligent systems (Baranes & Oudeyer, ; Oudeyer, Kaplan, & Hafner, ), and consequently a rapidly expanding body of computational and robotic work now focuses on the intrinsic motivation mechanisms that may underlie a range of behaviors; for example, low‐level perceptual encoding (Lonini et al., ; Schlesinger & Amso, ), novelty detection (Marsland, Nehmzow, & Shapiro, ), and motion planning (Frank, Leitner, Stollenga, Förster, & Schmidhuber, ).…”

Intrinsically motivated learning of visual motion perception and smooth pursuit

“…In that regard, one essential property of our model is that it is fully self-calibrating. In an analysis of the vergence model in [18], Lonini et al showed that the model can adapt to different kind of perturbations such as blur, or eye misalignments [21] [22]. This property is an important step towards autonomous robots capable of open ended learning.…”

An active-efficient-coding model of optokinetic nystagmus

“…Our model includes inputs from both foveal and peripheral regions of the retinae (Lonini et al, 2013). The fovea is assumed to be a square region subtending 7 degrees of visual angle and centered on the optical axis.…”