Quang

Open mind

[Masculine Path @masculinepath04]

I’m 33.

When I was young, I wasted years drinking, smoking, and being a degenerate.

Then I discovered Naval Ravikant and he changed my life forever.

Here are 20 teachings from the wisest person of this century (that will change your life forever):

[Jeannette Bohg @leto__jean]

Large Language Models promise to replace task planners in robotics.

But how do we verify that these plans are correct - especially for tasks that require long-horizon reasoning?

👇Check out Kevin's 🧵 on text2motion!

[Jia-Bin Huang @jbhuang0604]

How to come up with research ideas?

Excited about starting doing research but have no clue?🤷‍♂️🤷🏻‍♀️ Here are some simple methods that I found useful in identifying initial directions.

Check out the thread below 👇

[Jia-Bin Huang @jbhuang0604]

How to decide what to work on?

So many exciting ideas, so little time! How can one narrow down to a specific idea to work on? 🤔

Sharing some strategies I found useful. 🧵

[Fei-Fei Li @drfeifei]

Excited by this work! 👇 Led by my student @chenwang_j, Co-authors: @DrJimFan , @JiankaiSun, @RuohanZhang76, @drfeifei, @danfei_xu, @yukez and @AnimaAnandkumar.

[Aviv Tamar @AvivTamar1]

Enough games. The RL field needs to mature.

New blog post with @shiemannor
https://t.co/BANyQR50Iu

[AK @_akhaliq]

ORBIT: A Unified Simulation Framework for Interactive Robot Learning Environments

abs: https://t.co/7uWayJhbfd
project page: https://t.co/cqDh9xngwf

[Matthias Niessner @MattNiessner]

(1/n)
How to start a deep learning project?

We use a remarkably streamlined step-by-step process to set up deep learning projects. At the same time, people who are new to deep learning tend to always make the same (avoidable) mistakes.

Check out the thread below! 🧵

[Jeannette Bohg @leto__jean]

Back in Summer 2019, a group of Roboticists and Machine Learning Researchers met at the Robot Learning Summit in Montreal.

We had lively discussions on the Challenges and Opportunities for Embodied Intelligence.

Here are our thoughts: https://t.co/grRH6r33Zz

[Lin Shao @linshaonju]

Target networks in deep RL can slow down the learning process. Check out our algorithm GRAC without target networks at @corl_conf! Joint work with Yifan, Mengyuan, Shenli @shenli_yuan, Qingyun, and Jeannette @leto__jean. Codes in our project webpage:https://t.co/ucTCbPEE1d

[Sanjiban Choudhury @sanjibac]

Excited to share this talk on Interactive Imitation Learning that I gave at @Stanford Robotics Seminar.
Covers some of my current work at Aurora and future research that my lab at @CornellCIS will be focusing on!
https://t.co/b3dTETqyYk

[Kevin Zakka @kevin_zakka]

Tired of spending all day teleoperating your robot 🤖😡? Read on to learn how we can self-supervise reward functions from video demonstrations to teach robots new skills!

w @andyzengtweets @peteflorence @leto__jean @debidatta @JonathanTompson

[Stanford HAI @StanfordHAI]

In robotics, how do we fuse different sensor modalities together and what kind of information from each sensor is useful for a particular task? In last week’s HAI seminar, @leto__jean detailed her recent work on touch and vision for generalizability: https://t.co/ZFKVdkhnXM

[Jeannette Bohg @leto__jean]

To do daily chores, robots need to understand articulated objects. Sometimes a single picture of an object is deceiving. We propose a novel method that leverages temporal data to estimate the object articulation mechanism.

https://t.co/BBQFaSKOhh

🧵 1/9

[Rhys @rhys_newbury]

Very excited to share our new review paper on deep learning in grasping, focusing on 6-DoF grasping works.

Got to work with some great collaborators including @clembow @a__mousavian @Juxi @leto__jean

We hope the community can find our review useful!

https://t.co/m7fVnapgeh

[Jeannette Bohg @leto__jean]

Maybe I'm simplifying, but it seems that manipulation still seems difficult to scale in unstructured environments - especially in the space of sustainability/climate change

Often smart hardware solutions are useful for very specific tasks in a system.

Thoughts?

[Danny Driess @DannyDriess]

The recordings of our RSS 2022 Workshop on Implicit Representations for Robotic Manipulation are now online!

Playlist: https://t.co/uet6jCvFlX
Web: https://t.co/r4kFTqFnNb

Thanks again to our speakers @DanicaKragic @vincesitzmann @andyzengtweets @IMordatch @animesh_garg

[Jeannette Bohg @leto__jean]

How do you perform a manipulation task with a novel object that is heavily occluded?

We propose a method for task-driven in-hand manipulation of unknown objects with tactile sensing.

https://t.co/S2I9qNQXwT

🧵 1/n

[Jeannette Bohg @leto__jean]

People often use customized tools for a variety of manipulation tasks: 🥄🍴🥢🪛🪝🪓🛠️✂️🧵📎

We look at the problem of automatically designing customized tools for robots and leverage differentiable simulation and continual learning.

Video & Paper: https://t.co/al55p1S3fb

🧵

[Jeannette Bohg @leto__jean]

So many ways to generate a sequence of robot skills to solve a task that requires long-horizon reasoning: LLMs, task planners, high-level policies, …

But how do you ensure that each skill is executed such that the next skill can be successful at all?

https://t.co/QDpVZGRYxm