Yuri Feldman

Technion - Israel Institute of Technology | technion · Faculty of Computer Science

We introduce BIDCD - the Bosch Industrial Depth Completion Dataset. BIDCD is a new RGBD dataset of metallic industrial objects, collected with a depth camera mounted on a robotic manipulator. The main purpose of this dataset is to facilitate the training of domain-specific depth completion models, to be used in logistics and manufacturing tasks. We...

Depth cameras are a prominent perception system for robotics, especially when operating in natural unstructured environments. Industrial applications, however, typically involve reflective objects under harsh lighting conditions, a challenging scenario for depth cameras, as it induces numerous reflections and deflections, leading to loss of robustn...

In the context of semantic SLAM, we propose to represent the semantic information attached to objects (or generally, scenes) as continuous vectors in a latent space induced by a learned predictive observation model. We propose two observation models relating spatial changes in semantic measurements of an object to the latent object representation,...

Semantic perception can provide autonomous robots operating under uncertainty with more efficient representation of their environment and better ability for correct loop closures than only geometric features. However, accurate inference of semantics requires measurement models that correctly capture properties of semantic detections such as viewpoi...

We present an approach for localization and semantic mapping in ambiguous scenarios by incrementally maintaining a hybrid belief over continuous states and discrete classification and data association variables. Unlike existing incremental approaches we explicitly maintain data association components over time, allowing us to deal with perceptual a...

We propose an algorithm for robust visual classification of an object of interest observed from multiple views using a black-box Bayesian classifier which provides a measure of uncertainty, in the presence of significant ambiguity and classifier noise, and of localization error. The fusion of classifier outputs takes into account viewpoint dependen...