Kevin Lin

MS Computer Science at Stanford, advised by Jeannette Bohg; previously, EECS at UC Berkeley. I did research at Waabi, advised by Raquel Urtasun, and at Berkeley Artificial Intelligence Research with members of Pieter Abbeel's Robot Learning Lab. I also do research with Somil Bansal.

If you're interested in collaborating or getting into robotics, feel free to email!

Email  /  LinkedIn  /  Github

profile photo

I'm delighted by intelligent entities of all kinds. In particular, I'm interested in designing the brains of robots so they operate safely and effectively in the real world.

Text2Motion: From Natural Language Instructions to Feasible Plans
Kevin Lin, Christopher Agia, Toki Migimatsu, Marco Pavone, Jeannette Bohg,

Autonomous Robots '23 (Special Issue: Large Language Models in Robotics)
ICRA '23 Workshop on Pretraining for Robotics

We propose Text2Motion, a language-based planning framework enabling robots to solve sequential manipulation tasks that require long-horizon reasoning. Given a natural language instruction, our framework constructs both a task- and motion-level plan that is verified to reach inferred symbolic goals.

Partial-View Object View Synthesis via Filtering Inversion
Fan-Yun Sun, Jonathan Tremblay, Valts Blukis, Kevin Lin, Danfei Xu, Boris Ivanovic, Peter Karkus, Stan Birchfield, Dieter Fox, Ruohan Zhang, Yunzhu Li, Jiajun Wu, Marco Pavone, Nick Haber

International Conference on 3D Vision '24

We propose a framework that combines the strengths of generative modeling and network finetun-ing to generate photorealistic 3D renderings of real-world objects from sparse and sequential RGB inputs.

Active View Planning for Radiance Fields
Kevin Lin, Brent Yi,

RSS '22 Workshop on Implicit Representations for Robot Manipulation

We motivate, discuss, and present a study on the problem of view planning for radiance fields. We introduce a benchmark, active-3d-gym, for evaluating view planning algorithms for radiance field reconstructions and propose a simple solution to the view planning problem based on radiance field ensembles.

Combining optimal control and learning for autonomous aerial navigation in novel indoor environments
Kevin Lin, Brian Huo, Megan Hu,

Arxiv '21

We study how aerial robots can autonomously learn to navigate safely in novel indoor environments by combining optimal control and learning techniques. We train our agent entirely in simulation and demonstrate generalization on novel indoor scenes.

Beliefs and Level-k Reasoning in Traffic
E Vinitsky, A Filos, Kevin Lin, N Liu, N Lichtle, A Dragan, A Bayen, R McAllister, J Foerster,

4th NeurIPS Workshop on Emergent Communication

Occlusions present a major obstacle to guaranteeing safety in autonomous driving. Our key insight is that, sometimes, AV can get information about occluded regions by inferring over the actions of other agents on the road. We demonstrate that AVs can use this inferred data and level-K reasoning to avoid collisions with occluded pedestrians and drive in a pro-social manner.

Tesroo: A Redesigned Vacuum Robot

Won 1st place in UC Berkeley robotics course's final project

Envisioned and built a prototype vision-only robot vacuum using Visual SLAM to compete with LiDAR based Roomba models.

FLOW: A deep reinforcement learning framework for mixed autonomy traffic

Developed an open-source tool for applying ML techniques to autonomous vehicle driving policy discovery


Feel free to share your feedback here

cs170 Undergraduate Student Instructor, EE 126 Spring 2021

Probability and Random Processes

Undergraduate Student Instructor, CS 170 Fall 2020

Efficient Algorithms and Intractable Problems

Undergraduate Student Instructor, CS 70 Summer 2020

Discrete Math and Probability Theory