Related papers: FLIP: Flowability-Informed Powder Weighing

Recent years have witnessed impressive robotic manipulation systems driven by advances in imitation learning and generative modeling, such as diffusion- and flow-based approaches. As robot policy performance increases, so does the…

We perform experiments and discrete element simulations on the dosing of cohesive granular materials in a simplified geometry. The setup is a simplified canister box where the powder is dosed out of the box through the action of a…

Detection of slip during object grasping and manipulation plays a vital role in object handling. Existing solutions primarily rely on visual information to devise a strategy for grasping. However, for robotic systems to attain a level of…

CLIP has become a cornerstone of multimodal representation learning, yet improving its performance typically requires a prohibitively costly process of training from scratch on billions of samples. We ask a different question: Can we…

Particle Image Velocimetry (PIV) is an imaging technique in experimental fluid dynamics that quantifies flow fields around bluff bodies by analyzing the displacement of neutrally buoyant tracer particles immersed in the fluid. Traditional…

We apply reinforcement learning (RL) to robotics tasks. One of the drawbacks of traditional RL algorithms has been their poor sample efficiency. One approach to improve the sample efficiency is model-based RL. In our model-based RL…

CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves as the backbone of many generative pipelines, where a decoder is trained to map from the shared space…

Federated Class Incremental Learning (FCIL) is a new direction in continual learning (CL) for addressing catastrophic forgetting and non-IID data distribution simultaneously. Existing FCIL methods call for high communication costs and…

Robotic manipulation in high-precision tasks is essential for numerous industrial and real-world applications where accuracy and speed are required. Yet current diffusion-based policy learning methods generally suffer from low computational…

We study the problem of learning online packing skills for irregular 3D shapes, which is arguably the most challenging setting of bin packing problems. The goal is to consecutively move a sequence of 3D objects with arbitrary shapes into a…

Continual learning in robotics seeks systems that can constantly adapt to changing environments and tasks, mirroring human adaptability. A key challenge is refining dynamics models, essential for planning and control, while addressing…

Prompt learning is a powerful technique for transferring Vision-Language Models (VLMs) such as CLIP to downstream tasks. However, the prompt-based methods that are fine-tuned solely with base classes may struggle to generalize to novel…

We investigate pneumatic non-prehensile manipulation (i.e., blowing) as a means of efficiently moving scattered objects into a target receptacle. Due to the chaotic nature of aerodynamic forces, a blowing controller must (i) continually…

While imitation learning provides us with an efficient toolkit to train robots, learning skills that are robust to environment variations remains a significant challenge. Current approaches address this challenge by relying either on large…

This paper proposes a learning-from-demonstration method using probability densities on the workspaces of robot manipulators. The method, named "PRobabilistically-Informed Motion Primitives (PRIMP)", learns the probability distribution of…

With the increasing penetration of machine learning applications in critical decision-making areas, calls for algorithmic fairness are more prominent. Although there have been various modalities to improve algorithmic fairness through…

Robotic manipulation of flexible objects is widely required in both industrial and service applications. Among such objects, paper-like materials exhibit distinct mechanical characteristics compared to cloth, being more sensitive to…

Physics-informed deep learning has been developed as a novel paradigm for learning physical dynamics recently. While general physics-informed deep learning methods have shown early promise in learning fluid dynamics, they are difficult to…

Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy. Traditional FL methods often use a global model to fit all clients, assuming that clients' data are independent and…

Autonomous fabric manipulation is a longstanding challenge in robotics, but evaluating progress is difficult due to the cost and diversity of robot hardware. Using Reach, a cloud robotics platform that enables low-latency remote execution…