Diffusion and flow matching-based robot planners are slow and generate noisy and jerky trajectories.
@KL_Div7.4K followers
102,968 views
16 Comments
Comments from the original post on X (Twitter)

@KL_Div
Generative models, such as diffusion models and flow matching, are widely used for robot planning. The goal is to model the probability distribution over plausible future trajectories conditioned on the initial state. (2/7)
21 likes

@KL_Div
Our method uses Implicit Maximum Likelihood Estimation (IMLE) to train a one-step generative model on trajectories of varying quality. IMLE works by having each trajectory in the training dataset pull the closest generated trajectory towards it. (3/7)
13 likes

@KL_Div
Vanilla IMLE treats all trajectories in the training dataset equally despite their varying quality. Since our goal is to generate trajectories of high quality, we propose reward-weighted IMLE, which emphasizes trajectories with high reward more than those with low reward. (4/7)
8 likes

@KL_Div
We demonstrate on offline reinforcement learning tasks that our IMLE model runs in real time on both the CPU and GPU and achieves an order-of-magnitude speedup relative to diffusion models. (5/7)
8 likes

@KL_Div
We deploy our planner onboard a mobile robot and demonstrate real-time navigation in dynamic multi-agent environments. (6/7)
8 likes

@KL_Div
For more details, see: - Project website: - Paper: - Code: If you are at ICRA, come check out Poster 301 on Tuesday afternoon! (7/7)
24 likes

@InvntorV
Bruh diffusion models are really bad at generalizing in real-time , learnt a lot from your paper and I think I will find myself always going back to this. Who would have thought that the denoising process is the root cause. My initial thoughts were that without the de-noisers generalizations wouldn’t work or be optimal. This is great works and it is real time.
2 likes

@EmekaBuilds_
This is so nice ! 👏👏👏
1 like

@orielhaim
This is really cool! Are you looking for employees? Not for the salary I just like to play with things like this 🙃

@julleybuilds
Lil bro playing crossing road.

@_diginova
really cool

@MooncastOnline
boids demo?

@alperahmetoglu
Felt nostalgic. 2018, I was trying something like IMLE in the other KL direction, and was trying to find a way to prevent collapse. Then I stumbled upon IMLE. Cool idea! Will check this out.

@LSbyMO
Cool

@SAldwais
This is good it didn’t stop at all butterfly find a way while moving

@WendyCarlosa
looks like how the military would operate if the soldiers were cats