Jeudi 13 février 14h salle 9 de Condorcet, Peter Ford Dominey, DR CNRS du laboratoire CAPS UMR S INSERM 1093 équipe Robot Cognition Laboratory (RCL) présentera ses travaux intitulés : The Structuring Role of Language for Robot Perception and Action
Résumé : In the context of a robot such as the humanoid iCub, sensory input is of quite high dimension, and thus extracting pertinent information can be challenging. We can define psychologically-inspired simple perceptual primitives (e.g. contact, motion) that can be directly extracted from the visual signal from the robot cameras, and then use language to label structured sequences of incoming visual primitives to create a simple but robust action recognition system. The same principle can be applied to motor primitives that can be assembled using language labeling, in order to create a rich repertoire of actions. This structuring role of language can be applied at successively higher levels, corresponding to shared perceptual-motor plans that allow human robot cooperation. I will present some of our work in this area, and attempt to identify future opportunities for interaction.
Torsten Sattler de l’Université de Technologique de Chalmers (Suède) visitera l'ERL ViBot pour la soutenance de thèse de Nathan Piasco. A cette occasion, il nous présentera ses travaux le mardi 26 novembre 2019 à 10 dans l’amphi 8 du Centre Condorcet (Le Creusot).
Titre : Visual under Seasonal and Illumination Changes
Robustly perceiving the scene, independently of seasonal, illumination, and other changes, is a core requirement for any autonomous system operating in the real-world. In this talk, we will consider two tasks that require robust scene perception: Visual Localization and Semantic Segmentation, as well as their connection to each other. Starting with the visual localization problem of determining the pose of an autonomous system with respect to a scene representation, we explore two paradigms that can be used to localize images under strong changes in the viewing conditions:
1) Rather than designing representations, e.g., in the form of local features, that are invariant / robust to changes in the scene, domain adaption (for example in the form of generative neural networks) can be used to transform the current viewing conditions to a state close to the conditions under which the scene representation was constructed.
2) Rather than trying to predict how scenes evolve over time, invariant representations try to encapsulate the gist of a scene. In this talk, we consider semantic invariance, i.e., a fact that the semantic meaning of a scene should be invariant to seasonal and illumination changes.
The second approach relies on the assumption that semantic segmentations can be computed robustly under scene changes, which is often not true in practice. We thus discuss approaches to improve semantic segmentation performance using 3D geometry as a weakly supervisory signal.
Dans le cadre du projet PHC Sakura-Fullscan, Takuya Funatomi et Kenichiro Tanaka, du Optical Media Interface Lab (NAIST), visiteront l’ERL le 20 septembre 2018. A cette occasion, ils présenteront leurs travaux intitulés "Regression on Algebra of Geometric Transforms and its Applications" (T. Funatomi) et "Computational Imaging for Translucent Objects using Modulated Illumination" (K. Tanaka) à partir de 14h au Centre Universitaire Condorcet du Creusot.