Assistant Professor @Princeton. Developing robots that plan and learn to help people.
Joined October 2011
- Tweets 445
- Following 377
- Followers 3,332
- Likes 722
44 Photos and videos
This week's #PaperILike is "Multi-modal motion planning in non-expansive spaces" (Hauser & Latombe, IJRR 2010).
I learn more on every re-read of this foundational paper. Also appreciate the beautiful manifold figures!
PDF: ai.stanford.edu/~latombe/pap…
4
117
Jun 7
This week's #PaperILike is "Using Memory-Based Learning to Solve Tasks with State-Action Constraints" (Verghese & Atkeson, ICRA 2023).
Love the real-robot physical puzzle in this one.
Video of puzzle: youtube.com/watch?v=EzPeMsq1…
PDF: arxiv.org/abs/2303.04327
3
13
2,112
Jun 2
Gave ssik a try on our new Vega U from @DexmateAI. Seems to work great!
Fifteen years ago, I had the privilege of working with Rosen Diankov at CMU on his PhD thesis. The capstone was IKFast — for a generation of roboticists, the definition of what analytical inverse kinematics could be.
Today, I'm excited to release the next chapter: ssik.
1/
2
42
5,557
Tom Silver retweeted
Fifteen years ago, I had the privilege of working with Rosen Diankov at CMU on his PhD thesis. The capstone was IKFast — for a generation of roboticists, the definition of what analytical inverse kinematics could be.
Today, I'm excited to release the next chapter: ssik.
1/
1
7
80
20,321
May 31
This week's #PaperILike is "Plan-based Reward Shaping for Reinforcement Learning" (Grzes & Kudenko, 2008).
A nice combo of planning and RL that takes seriously the policy invariance ideas from Ng, Harada, & Russell (1999) [another paper I like!].
PDF: cs.kent.ac.uk/people/staff/m…
2
17
1,772
May 24
This week's #PaperILike is "QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?" (Li, Kim, & Wang, NeurIPS 2025).
Beautiful paper & increasingly important as agents start to ask more Qs. Curious how SOTA models do.
PDF: arxiv.org/abs/2503.22674
2
7
51
6,678
May 17
This week's #PaperILike is "Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary" (Asai & Fukunaga, AAAI 2018).
One of the key papers that got me hooked on learning planning before I started grad school.
PDF: arxiv.org/abs/1705.00154
8
92
6,758
May 17
I've noticed a feature of LLM writing; curious if it has a name. On advanced topics, LLMs connect two true statements with a "because" / "but" / "therefore" etc. -- but the two statements are not actually related. Hallucinonsequiturs?
4
1
19
2,210
May 10
This week's #PaperILike is "Human-Guided Complexity-Controlled Abstractions" (Peng et al., NeurIPS 2023).
Selecting the right levels and kinds of abstractions remains important and open for many forms of human-AI / human-robot interaction.
PDF: arxiv.org/abs/2310.17550
3
25
1,965
Tom Silver retweeted
3
14
67
14,736
Tom Silver retweeted
Last July, I started my role as founding co-director of the Princeton Robotics Initiative (w/ Aimy Wissa)!
We kicked things off with an inaugural symposium on our vision of humanity-driven robotics. Amazing to see the excitement, with 300 attendees and 80 posters! 🐯🤖
4
71
3,595
May 3
This week's #PaperILike is "HG-DAgger: Interactive Imitation Learning with Human Experts" (Kelly et al., 2019).
This would definitely be high on my list of "papers to read if you want to understand what robot foundation model startups are doing."
PDF: arxiv.org/abs/1810.02890
3
8
74
4,708
Tom Silver retweeted
Apr 30
Building autonomous robots that learn to reason and plan in the physical world is a long-standing problem.
We are excited to release KinDER, a large task suite and benchmark to bring different communities (TAMP, VLA, RL, etc.) together for this challenge!
Welcome to try it out!
Apr 30
Meet KinDER — a stress test for robot physical reasoning. All 13 methods failed 😈
🌎 25 environments
♾️ Infinite tasks
🏋️ Gymnasium API
⚒️ Over 20 parameterized skills
🪧 Human demonstrations
📊 13 baselines (planning and learning)
From @Princeton @CMU_Robotics @ICatGT @CambridgeMLG @nvidia @MIT_CSAIL
🧵 1/n
6
25
3,724
Tom Silver retweeted
Apr 30
KinDER is finally released 🎉
A step forward in defining what physical reasoning is and how to evaluate it, through many kinematic and dynamic manipulation challenges.
See @YixuanHuang13 post to learn more! See you at RSS!
Apr 30
Meet KinDER — a stress test for robot physical reasoning. All 13 methods failed 😈
🌎 25 environments
♾️ Infinite tasks
🏋️ Gymnasium API
⚒️ Over 20 parameterized skills
🪧 Human demonstrations
📊 13 baselines (planning and learning)
From @Princeton @CMU_Robotics @ICatGT @CambridgeMLG @nvidia @MIT_CSAIL
🧵 1/n
1
7
13
1,779
Tom Silver retweeted
There's so much infra that went into this project - tasks in MuJoCo/PyBullet/Pymunk, Parameterized Skills, LLM/VLM Planners, MPC, PPO, SAC, DP, VLAs, and more.
Kudos to the entire team for bringing this together! See you all at RSS :)
Apr 30
KinDER introduces five core physical reasoning challenges in dynamic & kinematic environments, both in 2D and 3D. These are bottlenecks for state-of-the-art robot planning and manipulation. Progress on KinDER will mean real progress for robotics.
🧵 2/n
4
19
1,890
Tom Silver retweeted
Apr 30
Long-horizon physical reasoning used to be the specialty of TAMP.
KinDER is a new sim benchmark that horizontally compares across paradigms, from VLA to PDDL bilevel planning to RL.
If you care about hard physical reasoning tasks, give KinDER a try!
To appear at RSS 2026.
Apr 30
Meet KinDER — a stress test for robot physical reasoning. All 13 methods failed 😈
🌎 25 environments
♾️ Infinite tasks
🏋️ Gymnasium API
⚒️ Over 20 parameterized skills
🪧 Human demonstrations
📊 13 baselines (planning and learning)
From @Princeton @CMU_Robotics @ICatGT @CambridgeMLG @nvidia @MIT_CSAIL
🧵 1/n
8
69
10,038
Tom Silver retweeted
Apr 30
As robot learning starts to mature, it’s important that we develop rigorous benchmarks to provide a North Star for progress and also compare a very wide variety of approaches. I think KinDER accomplishes both of these aims and more, and I’m excited to hopefully see fast progress on these tasks! 🤖
Apr 30
Meet KinDER — a stress test for robot physical reasoning. All 13 methods failed 😈
🌎 25 environments
♾️ Infinite tasks
🏋️ Gymnasium API
⚒️ Over 20 parameterized skills
🪧 Human demonstrations
📊 13 baselines (planning and learning)
From @Princeton @CMU_Robotics @ICatGT @CambridgeMLG @nvidia @MIT_CSAIL
🧵 1/n
4
26
2,271
Apr 30
As a planning learning researcher, I’m really excited about KinDER. It clarifies planning (especially TAMP) for outsiders, defines key open challenges for the field, and creates a common ground to compare & combined planning learning approaches. (1/n)
Apr 30
Meet KinDER — a stress test for robot physical reasoning. All 13 methods failed 😈
🌎 25 environments
♾️ Infinite tasks
🏋️ Gymnasium API
⚒️ Over 20 parameterized skills
🪧 Human demonstrations
📊 13 baselines (planning and learning)
From @Princeton @CMU_Robotics @ICatGT @CambridgeMLG @nvidia @MIT_CSAIL
🧵 1/n
2
11
76
7,168
Apr 30
Check out these environments and others (25 total) in the “KinDERGarden”: prpl-group.com/kinder-site
And look out for KinDER at RSS 2026! arxiv.org/abs/2604.25788
1
5
206
Apr 30
I also want to give a massive shout out to all the authors who put in an extraordinary engineering effort, especially the leaders @YixuanHuang13, @Bw_Li1024 , and @saxenavaibhav11 👏 (n/n)
4
189