Monroe Kennedy's Avatar

Monroe Kennedy

@mdkennedy3

Stanford professor developing collaborative robotics. Directs the Assistive Robotics and Manipulation lab (ARMLab) http://arm.stanford.edu

95
Followers
15
Following
32
Posts
22.02.2024
Joined
Posts Following

Latest posts by Monroe Kennedy @mdkennedy3

Post image

In our latest work Dexfriut dex-fruit.github.io we explore how our densetact sensor enables gentle manipulation of produce with many interactions and a quantitative visual metric leveraging Gaussian Splats to monitor damage on produce.

17.11.2025 20:55 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

2/n
We use Gaussian Splats for safe robot navigation: Splats model the scene, and their Gaussians act as repulsive barriers via control barrier functions to prevent collisions given requested inputs from the human teleoperator.

18.05.2025 01:08 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
LinkedIn This link will take you to a page that’s not on LinkedIn

1/n
"A Control Barrier Function for Safe Navigation with Online Gaussian Splatting Maps" Timothy Chen, Aiden Swann, Javier Yu, Ola Shorinwa, Riku Murai, Monroe Kennedy, Mac Schwager
#ICRA2025

ICRA Presentation day/location: 08:40 - 08:45 | Thu 22 May | 406 | ThAT18.3
Website: lnkd.in/gHA_NzEv

18.05.2025 01:07 πŸ‘ 2 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

2/n We efficiently build a high-quality Gaussian Splat by capturing initial views, generating a Splat, and using pose uncertainty in color and depth to guide the next best real-world view for scene reconstruction.

@peasant98.bsky.social

18.05.2025 01:06 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
LinkedIn This link will take you to a page that’s not on LinkedIn

1/n
"Next Best Sense: Guiding Vision and Touch with FisherRF for 3D Gaussian Splatting" Matthew Strong, Boshu Lei, Aiden Swann, Wen Jiang, Kostas Daniilidis, Monroe Kennedy
#ICRA2025!

ICRA Pres: 15:35 - 15:40 | Tue 20 May | 316 | TuCT13.5
Website: lnkd.in/g8DNUR2k
Video: lnkd.in/g7FfU8FD

18.05.2025 01:04 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0
J-PARSE: Jacobian-based Projection Algorithm for Resolving Singularities Effectively Vel-IK Control
J-PARSE: Jacobian-based Projection Algorithm for Resolving Singularities Effectively Vel-IK Control YouTube video by Stanford ARMLab

JPARSE for handling robot manipulator singularities!
jparse-manip.github.io
#AcademicSky #EDUSky #Robots

youtu.be/ZMrNGQht9eg?...

07.05.2025 19:41 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
J-PARSE: Jacobian-based Projection Algorithm for Resolving Singularities Effectively Vel-IK Control
J-PARSE: Jacobian-based Projection Algorithm for Resolving Singularities Effectively Vel-IK Control YouTube video by Stanford ARMLab

youtu.be/ZMrNGQht9eg?...

07.05.2025 17:01 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0
J-PARSE J-PARSE enables for the smooth entering and exiting of kinematic singularities for robotic manipulators.

(6/n) To learn more, read our paper and use our open-source code base, check out our interactive paper website: jparse-manip.github.io

07.05.2025 17:00 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

(5/n) Our method J-PARSE stands to improve robotic teleoperation control, improve embodiment in imitation learning, and allow robot upper limbs to move in a more 'natural' way like human counterparts.

07.05.2025 17:00 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

(4/n) This approach is motivated by the anthropomorphic motion of athletes such as baseball players who extend their hand towards their target for catching a ball, and they only consider the motion of their hand in this fast motion control.

07.05.2025 17:00 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

(3/n) Fewer methods still take you into singular poses and require very specific knowledge of the robot and its particular singular poses, as well as an accompanying strategy to exit these poses.

07.05.2025 16:59 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

(2/n) Robot manipulator singularities have been a challenge for roboticists for decades. Over the years, there have been many approaches to primarily avoid them and, in a few cases (such as damped least squares), approach them, albeit sacrificing pose accuracy at non-singular poses.

07.05.2025 16:59 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
J-PARSE J-PARSE enables for the smooth entering and exiting of kinematic singularities for robotic manipulators.

(1/n) In our work, J-PARSE @sguptasarma.bsky.social @peasant98.bsky.social @hao12450.bsky.social provide a method of entering singular poses, and if you start extremely close to singular poses (small float point value), the ability to exit the singular configuration as well.
jparse-manip.github.io

07.05.2025 16:58 πŸ‘ 1 πŸ” 0 πŸ’¬ 6 πŸ“Œ 0
J-PARSE: Jacobian-based Projection Algorithm for Resolving Singularities Effectively Vel-IK Control
J-PARSE: Jacobian-based Projection Algorithm for Resolving Singularities Effectively Vel-IK Control YouTube video by Stanford ARMLab

youtu.be/ZMrNGQht9eg?...

07.05.2025 16:49 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
J-PARSE J-PARSE enables for the smooth entering and exiting of kinematic singularities for robotic manipulators.

(6/n) To learn more, read our paper and use our open-source code base, check out our interactive paper website: jparse-manip.github.io and our paper video: youtu.be/ZMrNGQht9eg?...

07.05.2025 16:48 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

(5/n) Our method J-PARSE stands to improve robotic teleoperation control, improve embodiment in imitation learning, and allow robot upper limbs to move in a more 'natural' way like human counterparts.

07.05.2025 16:47 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

(4/n) This approach is motivated by the anthropomorphic motion of athletes such as baseball players who extend their hand towards their target for catching a ball, and they only consider the motion of their hand in this fast motion control.

07.05.2025 16:46 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

(3/n) Fewer methods still take you into singular poses and require very specific knowledge of the robot and its particular singular poses, as well as an accompanying strategy to exit these poses.

07.05.2025 16:46 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

(2/n) Robot manipulator singularities have been a challenge for roboticists for decades. Over the years, there have been many approaches to primarily avoid them and, in a few cases (such as damped least squares), approach them, albeit sacrificing pose accuracy at non-singular poses.

07.05.2025 16:45 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
Video thumbnail

Black in Robotics Student Travel Fellowships due 1/17/25
#BlackInRobotics #Fellowships #Awards @blackinengineering.bsky.social @blackinx.bsky.social
blackinrobotics.org/bir-student-...

08.01.2025 23:11 πŸ‘ 9 πŸ” 7 πŸ’¬ 0 πŸ“Œ 0

Latex (overleaf) is the way! Handles formatting and reference styles. For ref.bib:

\documentclass{article}
\usepackage[utf8]{inputenc}
\begin{document}

This is a citation \cite{example}.

\bibliographystyle{apa} % Switch this to "vancouver" or another style
\bibliography{ref}

\end{document}

08.01.2025 22:44 πŸ‘ 3 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
Video thumbnail

Collaborative #Robotics is the next frontier! The last few decades have focused on robotic autonomy, and we have seen some amazing things. But it's time for #Robotics to get to the hard tasks, less gimmicks, and more practical assistance and teammate understanding.
www.science.org/doi/full/10....

04.12.2024 17:52 πŸ‘ 3 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Our work appeared in #CORL2024

01.12.2024 19:10 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
Video thumbnail

#GaussianSplat are a fantastic new tool to visually represent a scene. By combining them with language models and semantics #Robots can perform manipulation tasks on command. Read more here: splatmover.github.io
#Robotics #Nerfs #research

01.12.2024 19:08 πŸ‘ 2 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0
Video thumbnail

Humans grasp objects from flat surfaces using a variety of methods: tapping, fingernail, pinch. Can #Robotics do the same? Check out our nominated best paper DenseTact-mini in #icra2024 that explores this: sites.google.com/view/denseta...

30.11.2024 16:09 πŸ‘ 1 πŸ” 1 πŸ’¬ 0 πŸ“Œ 0
BiR 3M MS Student Tuition Fellowship β€” blackinrobotics

#BlackSky #BlackSTEM #WomenSTEM #BlackInRobotics #BlackEduSky #AcademicSky #EduSky #BlackInX
Now available
blackinrobotics.org/bir-3m-ms-st... #BlackInRobotics #MSFellowship

24.11.2024 20:57 πŸ‘ 7 πŸ” 5 πŸ’¬ 0 πŸ“Œ 0
Video thumbnail

#Robotics can greatly improve #Prosthetics by endowing them with intelligence through advanced situational awareness and human intent estimation. Our work "ProACT: An Augmented Reality Testbed for Intelligent Prosthetic Arms" presents a virtual tested and control methods arm.stanford.edu/proact

29.11.2024 16:24 πŸ‘ 3 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

#Robotics #wearable #motionPrediction #assistiveRobotics

29.11.2024 01:07 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
Video thumbnail

Can a wearable sensor predict where you might walk? We present "Egocentric Scene-aware Human Trajectory Prediction" predicting someone's path from a front facing camera leveraging semantic information in the scene, learn more here: mmego.weizhuowang.com

29.11.2024 01:05 πŸ‘ 1 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0
Video thumbnail

#BlackSky #BlackSTEM #WomenSTEM #BlackInRobotics #BlackEduSky #AcademicSky #EduSky #BlackInX
Now available
blackinrobotics.org/bir-3m-ms-st... #BlackInRobotics #MSFellowship

24.11.2024 20:57 πŸ‘ 12 πŸ” 8 πŸ’¬ 0 πŸ“Œ 0