News & Events

3.08.2020

TASP PhD Seminar - Dmitry Kopitkov - "General Probabilistic Surface Optimization"

Work towards PhD degree under the supervision of Prof. Vadim Indelman

When: 31.8.2020 at 11:30

Where: Zoom

Abstract: Probabilistic inference, such as density (ratio) estimation, is a fundamental and highly important problem that needs to be solved in many different domains including robotics and computer science. Recently, a lot of research was done to solve it by producing various objective functions optimized over neural network (NN) models. Such Deep Learning (DL) based approaches include unnormalized and energy models, as well as critics of Generative Adversarial Networks, where DL has shown top approximation performance. In this research we contribute a novel algorithm family, which generalizes all above, and allows us to infer different statistical modalities (e.g. data likelihood and ratio between densities) from data samples. The proposed unsupervised technique, named Probabilistic Surface Optimization (PSO), views a model as a flexible surface which can be pushed according to loss-specific virtual stochastic forces, where a dynamical equilibrium is achieved when the pointwise forces on the surface become equal. Concretely, the surface is pushed up and down at points sampled from two different distributions, with overall up and down forces becoming functions of these two distribution densities and of force intensity magnitudes defined by the loss of a particular PSO instance. Upon convergence, the force equilibrium associated with the Euler-Lagrange equation of the loss enforces an optimized model to be equal to various statistical functions, such as data density, depending on the used magnitude functions. Furthermore, this dynamical-statistical equilibrium is extremely intuitive and useful, providing many implications and possible usages in probabilistic inference. We connect PSO to numerous existing statistical works which are also PSO instances, and derive new PSO-based inference methods as demonstration of PSO exceptional usability. Additionally, we investigate the impact of Neural Tangent Kernel (NTK) on PSO equilibrium. Our study of NTK dynamics during the learning process emphasizes the importance of the model kernel adaptation to the specific target function for a good learning approximation.

You can see the seminar here

 

30.07.2020

TASP MSc Seminar - Or Rivlin - "Generalized Planning with Deep Reinforcement Learning"

Work towards MSc degree under the supervision of Dr. Erez Karpas and Dr. Tamir Hazan

When: 2.9.2020 at 9:00

Where: zoom

Abstract:

A hallmark of intelligence is the ability to deduce general principles from examples, which are correct beyond the range of those observed. Generalized Planning deals with finding such principles for a class of planning problems, so that principles discovered using small instances of a domain can be used to solve much larger instances of the same domain. In this work we study the use of Deep Reinforcement Learning and Graph Neural Networks to learn such generalized policies and demonstrate that they can generalize to instances that are orders of magnitude larger than those they were trained on.

You can see the seminar here

20.05.2020

TASP MSc Seminar - Yotam Amitai - "Automatic Generation of Flexible Plans with Choice"

Work towards MSc degree under the supervision of Dr. Erez Karpas

When: 20.5.2020 at 14:30

Where: Zoom

Abstract:
Robots operating in the real world must deal with uncertainty, be it due to working with humans who are unpredictable, or simply because they must operate in a dynamic environment.
Ignoring the uncertainty could be dangerous, while accounting for all possible outcomes, as in contingent planning, is often computationally infeasible. One possibility, which lies between ignoring the uncertainty completely and addressing it completely is to use flexible plans with choice, formulated as Temporal Planning Networks (TPNs). This approach has been successfully demonstrated to work in human-robot teaming using the Pike executive, an online executive that unifies intent recognition and plan adaptation. However, one of the main challenges to using Pike is the need to manually specify the TPN. In this work, we address this challenge by describing a technique for automatically synthesizing a TPN which covers multiple possible executions for a given temporal planning problem specified in PDDL 2.1. Our approach starts by using a diverse planner to generate multiple plans, and then merges them into a single TPN. We show how to merge the diverse plans into a single TPN using constraint optimization. An empirical evaluation on a set of IPC benchmarks shows that our approach scales well, and generates TPNs which can generalize the set of plans they are generated from.

You can see the seminar here

Image for Graduation Ceremony, Class of 2016
13.06.2016

Graduation Ceremony, Class of 2016

The graduation ceremony of the Technion Autonomous Systems Program class of 2016 was held on 13.6.2016. We are proud of you and wish you all the best.

Image for Graduation Ceremony, Class of 2015
8.06.2015

Graduation Ceremony, Class of 2015

On June the 8th 2015, the first TASP graduate students have received their MSc. We are proud of you, and wish you all the best!

6.01.2015

Excellence Awards Given by Graduate School to TASP Students

The Graduate school has awarded excellence scholarships this year to four TASP students: Mr. Roei Elfassi, an M.Sc. student, and Mr. Guy Yona, a Ph.D., student received the Guthwirth Excellence Award: Mr. Tal Aharoni, an M.Sc student, received the Sherman Excellence Award: Ms. Mi La, a Ph.D student, received the Jacobs Excellence Award.

5.01.2015

First Student to Graduate from TASP

First TASP student to graduate is Mrs. Coral Moreno-Hirshfield, under the joint supervision of Prof. Pini Gurfil and Dr. Erez Ribak.