Machine Learning in Robotics

Detection Metrics

Set of tools to evaluate object detection neural networks models over the common object detection datasets.

Go!

Behavior Metrics

Different types of neural networks that allow learning behavior

Go!

Neural FPGA

Custom hardware able to do inference over generic neural networks using only open source tools.

Go!

Object Detector

Easily window which simultaneously shows on real-time the image captured from a webcam or video …

Go!

MachineLearning Projects

• Reinforcement Learning Studio GitHub
• Francisco Pérez (master): DeepLearning in autonomous vision based navigation of real robots.
• Nacho Arranz (master): Deep Reinforcement Learning for autonomous car.
• David Pascual, (master): Convolutional Pose Machines.
• Nuria Oyaga, (master): Predicting images, learning time sequences.
• Vanessa Fernández (master): Deep Learning for Visual Control.
• Alexandre Rodriguez (master): DeepLearning.
• Vinay Sharma (GSoC-2018) DeepLearning, DetectionSuite tool

Pretrained network models.

Challenges

Adding support for segmentation, more datasets and more DL frameworks.

The goal of this project is to expand the supported datasets (ImageNet, COCO…) and expand the neural frameworks (Keras, TensorFlow, Caffe…). In addition several detection architectures should be trained and compared with the new release of the tool.

The expected result is a new release of DetectionStudio tool extending the existing functionality for objection but also for two new deep learning problems: classification and segmentation including new statistics for each of them.