Roberto Calandra
@RCalandra
Followers
2K
Following
437
Media
13
Statuses
129
Professor at @lasr_lab of @tudresden_de -- Working in Machine Learning and Robotics.
Dresden, Germany
Joined July 2011
Bye Bye Twitter. You can still find me at
threads.com
14 Followers • 0 Threads • Full (W3) Professor at TU Dresden Head of the LASR Lab Researcher in Machine Learnings and Robotics. See the latest conversations with @dr.rcal.
1
0
1
Paper and design files are open-sourced at
digit.ml
Novel Designs for a Tactile Sensor with Application to In-Hand Manipulation
0
1
22
In addition, Digit360 has Edge AI capabilities to quickly process data locally and provide fast motor reflexes Digit360 is the result of many years of research with an amazing team - Mike Lambeta, @AIatMeta, @tudresden_de , @SECAI_School and @TactileInternet . (2/3)
0
2
11
I am very excited to introduce Digit360, our new super-human omnidirectional tactile sensor. Digit360 is truly multimodal (sensing forces as small as 1 mN, geometries down to 7 µm, vibrations to 9Khz, heat, and even smell). (1/3)
6
26
220
Researchers from @ias_tudarmstadt and @lasr_lab present a novel, open-source event-based optical #tactilesensor called Evetac. By applying this sensor, the researchers are able to create fast and robust closed-loop grasp controllers for manipulation. https://t.co/R6ejt8mPME
1
8
41
Excited to announce the first Touch Sensing and Processing Summer School hosted in Dresden on September 2-6. The summer school is sponsored by @SECAI_School and @TactileInternet. Accommodations and meals will be fully covered by the summer school. Apply at
1
1
22
Hearty congratulations to BAIR students, faculty and alumni for their many awards at #ICRA2024 this week in Japan BAIR alumni @pulkitology @LerrelPinto @RCalandra won Early Career awards; students from @svlevine @Ken_Goldberg @JitendraMalikCV labs won both Best Paper awards!
2
10
60
It is a great honor to receive here at ICRA 2024 in Yokohama the IEEE Early Academic Career Award from the Robotics and Automation Society. Thank you to all the splendid collaborators that made this research possible over the years.
22
4
141
Would like to do research in touch sensing, but don't have the right hardware? @AIatMeta is now accepting proposals to donate DIGIT sensors. Please apply at
digit.ml
Novel Designs for a Tactile Sensor with Application to In-Hand Manipulation
0
3
15
Collaboration between @AIatMeta, @Stanford, @DKFZ and @tudresden_de. Research partially supported by @SECAI_School and @TactileInternet.
0
0
8
Preliminary results show that our sensor, in conjunction with the right AI models, can detect cancer in real prostate tissue. In the future, we hope that this might lead to real-world medical applications.
2
0
26
We just released our new work on miniaturizing high-resolution tactile sensors using fiber optics, and open-sourced the new DIGIT Pinky sensor. Paper: https://t.co/9Hv7PndrvM Design: https://t.co/Nx3taPHdqD
13
51
322
Great collaboration with @Suddhus @mukadammh et al. on in-hand visuo-tactile SLAM.
NeuralFeels is just scratching the surface of what's possible possible with affordable vision and touch— here we focus on in-hand SLAM. Data/code will follow shortly, for more details check out
0
0
14
If you're generally excited about #robotics, catch up with our 6th (!!!) Robot Learning workshop on the 16th! 'Pretraining, Fine-Tuning, and Generalization with Large Scale Models' https://t.co/v1LKtPBv9C
robot-learning.ml
@NeurIPS 2023 16 Dec Hall B2
1
7
17
New white paper that connect the objective mismatch problem with LLMs, and argue why training with RLHF is problematic. Awesome collaboration with @natolambert
Why our current RLHF methods do not quite align with our actual goals, getting false refusals and hard to steer models: objective mismatch(s). The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback, with @RCalandra - new position paper / sort of
0
3
23
Excited to share some core RL work for a change (e.g. not LLMs, yet)! We present: A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning This paper is part review part synthesis of recent trends in model-based reinforcement learning. As you'll see in
4
10
60
🦾 Our robot hand can rotate objects over 6+ axes in the real-world! Introducing RotateIt (CoRL 2023), a Sim-to-Real policy that can rotate many objects over many axes, using vision and touch! Check it out: https://t.co/EqdSeSXFrj. Paper: https://t.co/8eTWPIVfRS.
#CoRL2023
8
26
179
📢 Announcing 1st "Workshop on Touch Processing: a new Sensing Modality for AI" at NeurIPS 2023. If you are interested in touch sensing & machine learning, don’t miss the opportunity to submit your work and participate! 📷 Call for Papers: https://t.co/DsSFGPyIBK.
#NeurIPS2023
1
3
14
You can now more easily save and share your MBRL agents & dynamics models in MBRL-Lib. I hope this helps build new research programs around re-using compute. Huge shoutout to @ShivaSujit for pushing this through.
2
6
41
We have several open positions for Postdocs and PhD students on topics such as reinforcement learning, robotic manipulation, and tactile sensing. If you are interested, please visit
1
2
20