www.ias.informatik.tu-darmstadt.de Open in urlscan Pro
130.83.164.25  Public Scan

Form analysis
1 forms found in the DOM

GET https://www.ias.informatik.tu-darmstadt.de/Site/Search

<form class="search-box" role="search" id="fs_top" action="https://www.ias.informatik.tu-darmstadt.de/Site/Search" method="get">
  <input type="hidden" name="pagename" value="Site/Search">
  <input class="wikisearchbox" type="text" placeholder="Search" aria-label="Search" name="q" value="">
  <button class="nav-link-icon"><i class="fas fa-search"></i></button>
</form>

Text Content

 * Team Team
    * Current Members
    * Off-Campus Students
    * Alumni

 * Research Research
    * Overview
    * Our Robots
    * Robot Videos
    * Funded Projects

 * Publications Publications
    * Publications by Year
    * Publications by Type
    * PhD Theses
    * Patents

 * Talks Talks
    * Upcoming
    * Past

 * Teaching Teaching
    * Overview
    * Robot Learning Lecture
    * Robot Learning IP
    * Humanoid Robotics Seminar
    * Research Oberseminar

 * Theses Theses
    * New, Open Topics
    * Ongoing Theses
    * Completed Theses
    * External Theses
    * Advice for Thesis Students
    * Thesis Checklist and Template

 * Jobs Jobs
    * Jobs and Open Positions
    * Current Openings
    * Information for Applicants
    * Application Website
    * TU Darmstadt Student Hiwi Jobs

 * Contact Contact
    * Contact Information


 * Team
    * Current Members
    * Off-Campus Students
    * Alumni

 * Research
    * Overview
    * Our Robots
    * Robot Videos
    * Funded Projects

 * Publications
    * Publications by Year
    * Publications by Type
    * PhD Theses
    * Patents

 * Workshops
    * Overview
    * IWIALS
    * HRI 2024

 * Talks
    * Upcoming
    * Past

 * Teaching
    * Overview
    * Robot Learning Lecture
    * Robot Learning IP
    * Humanoid Robotics Seminar
    * Research Oberseminar

 * Theses
    * New, Open Topics
    * Ongoing Theses
    * Completed Theses
    * External Theses
    * Advice for Thesis Students
    * Thesis Checklist and Template

 * Jobs
    * Jobs and Open Positions
    * Current Openings
    * Information for Applicants
    * Application Website
    * TU Darmstadt Student Hiwi Jobs

 * Contact
    * Contact Information

   


INTELLIGENT AUTONOMOUS SYSTEMS

UPCOMING TALKS

DateTimeLocation9.01.202417:30-18:30http://talks.robot-learning.net Wil Thomason
(RICE), Invited Talk: Motions in Microseconds via Vectorized Sampling-Based
Planning DateTimeLocation19.01.202414:00-15:00http://talks.robot-learning.net
Moritz Grosse-Wentrup (Uni Wien), Invited Talk: Neuro-Cognitive Multilevel
Causal Modeling - A Framework that Bridges the Explanatory Gap be tween Neuronal
Activity and Cognition
DateTimeLocation19.01.202415:00-15:30http://talks.robot-learning.net Han Gao,
M.Sc. Thesis Defense: AffordanceParts: Learning Explainable Object Parts with
Invertible Neural Networks

Welcome to the Intelligent Autonomous Systems Group of the Computer Science
Department of the Technische Universitaet Darmstadt. Our research centers around
the goal of bringing advanced motor skills to robotics using techniques from
machine learning and control. Please check out our research or contact our lab
members.

Creating autonomous robots that can learn to assist humans in situations of
daily life is a fascinating challenge for machine learning. While this aim has
been a long-standing vision of artificial intelligence and the cognitive
sciences, we have yet to achieve the first step of creating robots that can
learn to accomplish many different tasks triggered by environmental context or
higher-level instruction. The goal of our robot learning laboratory is the
realization of a general approach to motor skill learning, to get closer towards
human-like performance in robotics. We focus on the solution of fundamental
problems in robotics while developing machine-learning methods. Artificial
agents that autonomously learn new skills from interaction with the environment,
humans or other agents will have a great impact in many areas of everyday life,
for example, autonomous robots for helping in the household, care of the elderly
or the disposal of dangerous goods.

An autonomously learning agent has to acquire a rich set of different behaviours
to achieve a variety of goals. The agent has to learn autonomously how to
explore its environment and determine which are the important features that need
to be considered for making a decision. It has to identify relevant behaviours
and needs to determine when to learn new behaviours. Furthermore, it needs to
learn what are relevant goals and how to re-use behaviours in order to achieve
new goals. In order to achieve these objectives, our research concentrates on
hierarchical learning and structured learning of robot control policies,
information-theoretic methods for policy search, imitation learning and
autonomous exploration, learning forward models for long-term predictions,
autonomous cooperative systems and biological aspects of autonomous learning
systems.

In the Intelligent Autonomous Systems Institute at TU Darmstadt is headed by Jan
Peters, we develop methods for learning models and control policy in real time,
see e.g., learning models for control and learning operational space control. We
are particularly interested in reinforcement learning where we try push the
state-of-the-art further on and received a tremendous support by the RL
community. Much of our research relies upon learning motor primitives that can
be used to learn both elementary tasks as well as complex applications such as
grasping or sports. In addition, there are research groups by Carlo d'Eramo,
Dorothea Koert and Joni Pajarinen at our institute that also focus on these
aspects.




DIRECTIONS AND OPEN POSITIONS

In case that you are searching for our address or for directions on how to get
to our lab, look at our contact information. We always have thesis opportunities
for enthusiastic and driven Masters/Bachelors students (please contact Jan
Peters). Check out the open topics currently offered theses (Abschlussarbeiten)
or suggest one yourself, drop us a line by email or simply drop by! We also
occasionally have open Ph.D. or Post-Doc positions, see OpenPositions.

For current news, see our Twitter feed ... our past news before Twitter is also
around.


244276
6
157090
Untitled Widget
yourwebsite.com
100%
1000

upcoming
250
Century Gothic, sans-serif
0
0
0
0
0
#ffffff
25
#ebff00
0
17
#9c8b69
#555555
#3480dc
#a2bec4
0
#435b77
#ffffff
#3480dc
#ffffff
#ffffff
#ffffff



#a08854
#ffffff
#777772
#ffffff
#a08854
#ffffff
#2c1c24
#ffffff
Read More
Get Tickets
2020-09-09 14:14:48
2020-09-09 14:17:01
Maaliwalas Theme
ias_tudarmstadt
Upcoming Events
Past Events
Calendar
Close Details
Hosted By
Prev Month
Next Month
0
View Full Map
View On Facebook
0
0

20
3
1
1
1
1
1
1
1
1
1
0
5
Follow
Posts
Followers
Following
Load more posts
0
1
End of posts.
View on Instagram
0
Favorites
1
#ffffff
View on Twitter
#555555
1
1
1
1
1
1
1
#ffffff
1
2
#000000
#3480dc
#000000

#000000
#555555
0.6
1
1
0
380
#ffffff
#212529
#0280fe
30

#


null
244276

null


0
null







null


@ias_tudarmstadt
281 Posts2714 Followers272 Following
Intelligent Autonomous Systems Group Intelligent Autonomous Systems Group
@TUDarmstadt working on Robot Learning, the intersection of Robotics and Machine
Learning. Lead by Prof. @Jan_R_Peters
http://www.ias.informatik.tu-darmstadt.de
Follow

@ias_tudarmstadt

The Robot Air Hockey Challenge is kicking off now in Room 353, and will feature
talks from the participants, Chris Atkeson and
@svlevine
! #NeurIPS2023
 2 11 10d
ias_tudarmstadt@ias_tudarmstadt
Dec 15, 2023
The Robot Air Hockey Challenge is kicking off now in Room 353, and will feature
talks from the participants, Chris Atkeson and @svlevine ! #NeurIPS2023

 2
 11

@ias_tudarmstadt

We're excited to present several works at #NeurIPS2023 this week, ranging from
approximate inference to tactile sensing! Check out the thread below for more
info
 10 35 16d
ias_tudarmstadt@ias_tudarmstadt
Dec 9, 2023
We're excited to present several works at #NeurIPS2023 this week, ranging from
approximate inference to tactile sensing! Check out the thread below for more
info

 10
 35

@ias_tudarmstadt

sites.google.com
 1 2 16d
ias_tudarmstadt@ias_tudarmstadt
Dec 9, 2023
sites.google.com

 1
 2

@ias_tudarmstadt

Introducing LocoMuJoCo, the first imitation learning benchmark tailored towards
locomotion! It comes with a diverse set of environments ranging from
musculoskeletal models to the brand-new @UnitreeRobotics H1 robot, and also many
motion capture datasets! https://github.com/robfiras/loco-mujoco…
 1 3 16d
ias_tudarmstadt@ias_tudarmstadt
Dec 9, 2023
Introducing LocoMuJoCo, the first imitation learning benchmark tailored towards
locomotion! It comes with a diverse set of environments ranging from
musculoskeletal models to the brand-new @UnitreeRobotics H1 robot, and also many
motion capture datasets! github.com/robfiras/loco-

 1
 3

@ias_tudarmstadt

We're presenting several papers at #IROS2023 this week! [1/5]
 3 16 3mo
ias_tudarmstadt@ias_tudarmstadt
Oct 2, 2023
We're presenting several papers at #IROS2023 this week! [1/5]

 3
 16
Your browser does not support HTML5 video.

@ias_tudarmstadt

Placing by Touching: An empirical study on the importance of tactile sensing for
precise object placing Luca Lach,  
@n_w_funk
,  Robert Haschke, Severin Lemaignan, Helge Joachim Ritter,
@Jan_R_Peters
&
@GeorgiaChal
Website: https://sites.google.com/view/placing-by-touching…

[4/5]
 2 5 3mo
ias_tudarmstadt@ias_tudarmstadt
Oct 2, 2023
Placing by Touching: An empirical study on the importance of tactile sensing for
precise object placing Luca Lach,  @n_w_funk,  Robert Haschke, Severin
Lemaignan, Helge Joachim Ritter, @Jan_R_Peters & @GeorgiaChal Website:
sites.google.com/view/placing-b

[4/5]

 2
 5
Your browser does not support HTML5 video.

@ias_tudarmstadt

Upon popular requests, we just released the standalone Sinkhorn Step implemented
in JAX, a generic solver for non-convex optimization problems. The MPOT
repository (in PyTorch) will also be released soon! Paper:
https://ias.informatik.tu-darmstadt.de/uploads/Team/AnThaiLe/mpot_preprint.pdf…
ssax: https://github.com/anindex/ssax
 3 3mo
ias_tudarmstadt@ias_tudarmstadt
Oct 2, 2023
Upon popular requests, we just released the standalone Sinkhorn Step implemented
in JAX, a generic solver for non-convex optimization problems. The MPOT
repository (in PyTorch) will also be released soon! Paper:
ias.informatik.tu-darmstadt.de/uploads/Team/A ssax: github.com/anindex/ssax

 3

@ias_tudarmstadt

Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion
Models João Carvalho,
@an_thai_le
, Mark Baeirl, Dorothea Koert &
@Jan_R_Peters
Paper: https://arxiv.org/abs/2308.01557

Site: https://sites.google.com/view/mp-diffusion…

[3/5]
 1 8 3mo
ias_tudarmstadt@ias_tudarmstadt
Oct 2, 2023
Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion
Models João Carvalho, @an_thai_le, Mark Baeirl, Dorothea Koert & @Jan_R_Peters
Paper: arxiv.org/abs/2308.01557

Site: sites.google.com/view/mp-diffus

[3/5]

 1
 8

@ias_tudarmstadt

Check out Hamish's latest work on bandits, accepted as an oral at this years
NeurIPS!
 1 9 3mo
ias_tudarmstadt@ias_tudarmstadt
Sep 26, 2023
Check out Hamish's latest work on bandits, accepted as an oral at this years
NeurIPS!

 1
 9

@ias_tudarmstadt


 12 3mo
ias_tudarmstadt@ias_tudarmstadt
Sep 14, 2023

 12

@ias_tudarmstadt

Last week we scaled up our annual retreat to over 100 participants! When we
weren’t in the mountains, we enjoyed many excellent talks from the likes of
@__jzhu__
,
@nathanlepora
,
@RCalandra
,
@herkevanhoof
and many more!
 4 37 4mo
ias_tudarmstadt@ias_tudarmstadt
Aug 26, 2023
Last week we scaled up our annual retreat to over 100 participants! When we
weren’t in the mountains, we enjoyed many excellent talks from the likes of
@__jzhu__, @nathanlepora, @RCalandra, @herkevanhoof and many more!

 4
 37

@ias_tudarmstadt

Check out the current leaderboard of the #RobotAirHockeyChallenge
…https://air-hockey-challenge.robot-learning.net/leaderboard One of the best
current submissions is shown below The deadline of this stage is the 11th of
August, so submit your agents!
 6 35 5mo
ias_tudarmstadt@ias_tudarmstadt
Jul 14, 2023
Check out the current leaderboard of the #RobotAirHockeyChallenge
r-hockey-challenge.robot-learning.net/leaderboard One of the best current
submissions is shown below The deadline of this stage is the 11th of August, so
submit your agents!

 6
 35
Your browser does not support HTML5 video.

@ias_tudarmstadt

An is at
@l4dc_conf
this week presenting his work (w/
@kay_hansel
,
@GeorgiaChal
&
@Jan_R_Peters
) on using optimal transport for planning and reactive control Paper:
https://arxiv.org/abs/2212.01938

 4 19 6mo
ias_tudarmstadt@ias_tudarmstadt
Jun 14, 2023
An is at @l4dc_conf this week presenting his work (w/ @kay_hansel, @GeorgiaChal
& @Jan_R_Peters) on using optimal transport for planning and reactive control
Paper: arxiv.org/abs/2212.01938


 4
 19
Your browser does not support HTML5 video.

@ias_tudarmstadt

Air Hockey news! 1. The challenge is now part of the #NeurIPS2023 competition
track! Stay tuned for updates. 2. The Qualifying Stage of the
#RobotAirHockeyChallenge has started! Join our challenge and work on a realistic
robotic platform. Register by 11th Aug. [1/4]
 9 30 7mo
ias_tudarmstadt@ias_tudarmstadt
Jun 6, 2023
Air Hockey news! 1. The challenge is now part of the #NeurIPS2023 competition
track! Stay tuned for updates. 2. The Qualifying Stage of the
#RobotAirHockeyChallenge has started! Join our challenge and work on a realistic
robotic platform. Register by 11th Aug. [1/4]

 9
 30
Your browser does not support HTML5 video.

@ias_tudarmstadt

16 qualified teams that meet the 'deployability' requirements will join the
tournament. Train an agent and compete against other teams! A 'double round
robin' schedule allows you to increase the robustness of your agent to different
opponents. [3/4]
 1 2 7mo
ias_tudarmstadt@ias_tudarmstadt
Jun 6, 2023
16 qualified teams that meet the 'deployability' requirements will join the
tournament. Train an agent and compete against other teams! A 'double round
robin' schedule allows you to increase the robustness of your agent to different
opponents. [3/4]

 1
 2

@ias_tudarmstadt

For more details, visit our website
…https://air-hockey-challenge.robot-learning.net [4/4]
 2 3 7mo
ias_tudarmstadt@ias_tudarmstadt
Jun 6, 2023
For more details, visit our website r-hockey-challenge.robot-learning.net [4/4]
 2
 3

@ias_tudarmstadt

We're at #ICRA2023 this week with papers on diffusion models, reactive robot
control, safe reinforcement learning and stable learning from demonstrations!
[1/5]
 4 31 7mo
ias_tudarmstadt@ias_tudarmstadt
Jun 1, 2023
We're at #ICRA2023 this week with papers on diffusion models, reactive robot
control, safe reinforcement learning and stable learning from demonstrations!
[1/5]

 4
 31

@ias_tudarmstadt

Hierarchical Policy Blending as Inference for Reactive Robot Control
@kay_hansel
@theCamusean
@GeorgiaChal
@Jan_R_Peters
https://arxiv.org/abs/2210.07890 https://sites.google.com/view/hipbi
 1 6 7mo
ias_tudarmstadt@ias_tudarmstadt
Jun 1, 2023
Hierarchical Policy Blending as Inference for Reactive Robot Control @kay_hansel
@theCamusean @GeorgiaChal @Jan_R_Peters arxiv.org/abs/2210.07890
sites.google.com/view/hipbi

 1
 6

@ias_tudarmstadt

Learning Stable Vector Fields on Lie Groups
@theCamusean
@davide_tateo
@Jan_R_Peters
https://arxiv.org/abs/2110.11774
 1 4 7mo
ias_tudarmstadt@ias_tudarmstadt
Jun 1, 2023
Learning Stable Vector Fields on Lie Groups @theCamusean @davide_tateo
@Jan_R_Peters arxiv.org/abs/2110.11774

 1
 4

@ias_tudarmstadt

Safe reinforcement learning of dynamic high-dimensional robotic tasks:
Navigation, manipulation, interaction.
@liu_puze
@SnehalJauhri
@davide_tateo
@GeorgiaChal
@Jan_R_Peters
https://arxiv.org/abs/2209.13308
https://puze-personal.web.app/talks/ICRA-video.html…
 1 5 7mo
ias_tudarmstadt@ias_tudarmstadt
Jun 1, 2023
Safe reinforcement learning of dynamic high-dimensional robotic tasks:
Navigation, manipulation, interaction. @liu_puze @SnehalJauhri @davide_tateo
@GeorgiaChal @Jan_R_Peters arxiv.org/abs/2209.13308
puze-personal.web.app/talks/ICRA-vid

 1
 5
Load more posts
Embed Twitter Profile on your website