Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Recent advancements in robot learning have used imitation learning with large models and extensive demonstrations to develop effective policies. However, these models are often limited by the quantity, quality, and diversity of demonstrations. This paper explores improving offline-trained imitation learning models through online interactions with the environment. We introduce Policy Decorator, which uses a model-agnostic residual policy to refine large imitation learning models during online interactions. By implementing controlled exploration strategies, Policy Decorator enables stable, sample-efficient online learning. Our evaluation spans eight tasks across two benchmarks-ManiSkill and Adroit-and involves two state-of-the-art imitation learning models (Behavior Transformer and Diffusion Policy). The results show Policy Decorator effectively improves the offline-trained policies and preserves the smooth motion of imitation learning models, avoiding the erratic behaviors of pure RL policies. See our project page (https://policydecorator.github.io) for videos.

Universal Trajectory Optimization Framework for Differential-Driven Robot Class

Differential-driven robots are widely used in various scenarios thanks to their straightforward principle, from household service robots to disaster response field robots. There are several different types of deriving mechanisms considering the real-world applications, including two-wheeled, four-wheeled skid-steering, tracked robots, etc. The differences in the driving mechanism usually require specific kinematic modeling when precise controlling is desired. Furthermore, the nonholonomic dynamics and possible lateral slip lead to different degrees of difficulty in getting feasible and high-quality trajectories. Therefore, a comprehensive trajectory optimization framework to compute trajectories efficiently for various kinds of differential-driven robots is highly desirable. In this paper, we propose a universal trajectory optimization framework that can be applied to differential-driven robot class, enabling the generation of high-quality trajectories within a restricted computational timeframe. We introduce a novel trajectory representation based on polynomial parameterization of motion states or their integrals, such as angular and linear velocities, that inherently matching robots' motion to the control principle for differential-driven robot class. The trajectory optimization problem is formulated to minimize complexity while prioritizing safety and operational efficiency. We then build a full-stack autonomous planning and control system to show the feasibility and robustness. We conduct extensive simulations and real-world testing in crowded environments with three kinds of differential-driven robots to validate the effectiveness of our approach. We will release our method as an open-source package.

LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud

In the current user-server interaction paradigm of prompted generation with large language models (LLM) on cloud, the server fully controls the generation process, which leaves zero options for users who want to keep the generated text to themselves. We propose LatticeGen, a cooperative framework in which the server still handles most of the computation while the user controls the sampling operation. The key idea is that the true generated sequence is mixed with noise tokens by the user and hidden in a noised lattice. Considering potential attacks from a hypothetically malicious server and how the user can defend against it, we propose the repeated beam-search attack and the mixing noise scheme. In our experiments we apply LatticeGen to protect both prompt and generation. It is shown that while the noised lattice degrades generation quality, LatticeGen successfully protects the true generation to a remarkable degree under strong attacks (more than 50% of the semantic remains hidden as measured by BERTScore).

Scalable neural network models and terascale datasets for particle-flow reconstruction

We study scalable machine learning models for full event reconstruction in high-energy electron-positron collisions based on a highly granular detector simulation. Particle-flow (PF) reconstruction can be formulated as a supervised learning task using tracks and calorimeter clusters or hits. We compare a graph neural network and kernel-based transformer and demonstrate that both avoid quadratic memory allocation and computational cost while achieving realistic PF reconstruction. We show that hyperparameter tuning on a supercomputer significantly improves the physics performance of the models. We also demonstrate that the resulting model is highly portable across hardware processors, supporting Nvidia, AMD, and Intel Habana cards. Finally, we demonstrate that the model can be trained on highly granular inputs consisting of tracks and calorimeter hits, resulting in a competitive physics performance with the baseline. Datasets and software to reproduce the studies are published following the findable, accessible, interoperable, and reusable (FAIR) principles.

Uncertainty-Aware Lung Nodule Segmentation with Multiple Annotations

Since radiologists have different training and clinical experience, they may provide various segmentation maps for a lung nodule. As a result, for a specific lung nodule, some regions have a higher chance of causing segmentation uncertainty, which brings difficulty for lung nodule segmentation with multiple annotations. To address this problem, this paper proposes an Uncertainty-Aware Segmentation Network (UAS-Net) based on multi-branch U-Net, which can learn the valuable visual features from the regions that may cause segmentation uncertainty and contribute to a better segmentation result. Meanwhile, this network can provide a Multi-Confidence Mask (MCM) simultaneously, pointing out regions with different segmentation uncertainty levels. We introduce a Feature-Aware Concatenation structure for different learning targets and let each branch have a specific learning preference. Moreover, a joint adversarial learning process is also adopted to help learn discriminative features of complex structures. Experimental results show that our method can predict the reasonable regions with higher uncertainty and improve lung nodule segmentation performance in LIDC-IDRI.