RoboPapers

Chris Paxton & Michael Cho geek out over robotic papers with paper authors.

Ep#24 CLONE: Closed-Loop Whole-Body Humanoid Teleoperation for Long-Horizon Tasks

Geeking out with Yixuan & Siyuan on CLONE:Closed-Loop Whole-Body Humanoid Teleoperation for Long-Horizon Taskshttps://humanoid-clone.github.ioCo-hosted by Chris Paxton & Michael Cho

08-05
01:07:00

Ep#23 FALCON - Learning Force-Adaptive Humanoid Loco-Manipulation

Geeking out with Yuanhang Zhang on FALCON - Learning Force-Adaptive Humanoid Loco-Manipulation https://lecar-lab.github.io/falcon-humanoid/Co-hosted by Chris Paxton & Michael Cho

08-05
41:54

Ep#22 DexWild: Dexterous Human Interactionsfor In-the-Wild Robot Policies

Geeking out with Tony Tao & Mohan Kumar Srirama on https://dexwild.github.ioCo-hosted by Michael Cho & Chris Paxton

07-28
01:03:00

Ep#21 TesserAct: Learning 4D Embodied World Models

Geeking out with Haoyu Zhen on TesserAct: Learning 4D Embodied World Models https://tesseractworld.github.io Co-hosted by Michael Cho & Chris Paxton

07-16
59:44

Ep#20 VideoMimic

Geeking out with Arthur Allshire & Hongsuk Choi on VideoMimic https://www.videomimic.netCo-hosted by Chris Paxton & Michael Cho

07-13
01:13:22

Ep#19 Learning to Drive from a World Model

Geeking out with Harald Schäfer on Learning to Drive from a World Model https://blog.comma.ai/mlsimCo-hosted by Chris Paxton & Michael Cho

07-13
50:34

Ep#17 EgoZero: Robot Learning from Smart Glasses

Geeking out with Vincent Liu, Ademi Adeniji on EgoZero:Robot Learning from Smart Glasses https://egozero-robot.github.io/Co-hosted by Chris Paxton & Michael Cho

06-26
01:11:01

Ep#16 TWIST: Teleoperated Whole-Body Imitation System

Geeking out with Yanjie on TWIST: Teleoperated Whole-Body Imitation System https://yanjieze.com/TWIST/ Co-hosted Chris Paxton & Michael Cho

06-25
43:24

Ep#15 Navigation World Models

Geeking out with Amir Bar on Navigation World Models https://amirbar.net/nwm/ Co-hosted by Chris Paxton & Michael Cho

06-25
54:40

Ep#14 VERTIFORMER: A Data-Efficient Multi-Task Transformer on Vertically Challenging Terrain

Geeking out with Xuesu Xiao on In-Air Vehicle Maneuver for High-Speed Off-Road Navigation https://cs.gmu.edu/~xiao/papers/dom_phli.pdf & VERTIFORMER: A Data-Efficient Multi-Task Transformer on Vertically Challenging Terrain https://cs.gmu.edu/~xiao/papers/vertiformer.pdf Co-hosted by Chris Paxton & Michael Cho

06-16
01:08:23

Ep#13 Instant Policy: In-Context Imitation Learning via Graph Diffusion

Geeking out with Vitalis Vosylius & Edward Johns​ on Instant Policy: In-Context Imitation Learning via Graph Diffusion https://www.robot-learning.uk/instant-policy

06-12
01:08:36

Ep#12 VaViM and VaVAM: Autonomous Driving through Video Generative Modeling

Geeking out with Florent Bartoccioni on VaViM and VaVAM: Autonomous Driving through Video Generative Modeling https://valeoai.github.io/vavim-vavam/

06-10
01:08:42

Ep#11 Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation

Geeking with the authors of Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation https://co-training.github.io

06-10
01:01:55

Ep#10 Humanoid Policy ~ Human Policy

Geeking out with Roger Qiu on Humanoid Policy ~ Human Policy https://human-as-robot.github.io

06-10
01:01:02

Ep#9: AutoEval - Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World

Geeking out with Paul Zhou on AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World https://auto-eval.github.io Co-hosted by Chris Paxton & Michael Cho

05-25
51:45

Ep#8: VGGT - Visual Geometry Grounded Transformer

Geeking out with Jianyuan on https://vgg-t.github.io

05-02
58:37

Ep#6: FP3: A 3D Foundation Policy for Robotic Manipulation

3d-foundation-policy.github.io

04-24
53:05

Ep#5: R+X: Retrieval & Execution from Human Videos

https://robot-learning.uk/r-plus-x

04-24
01:00:29

Ep#4: Vision Language Models are In-Context Value Learners

Geeking out with @JasonMa2020 on https://generative-value-learning.github.io (Vision Language Models are In-Context Value Learners)Co-hosted by @chris_j_paxton & @micoolcho

04-08
01:11:52

Recommend Channels