21 accepted papers
We introduce DriveAgent, a modular multi-agent autonomous driving framework that leverages large language model (LLM) reasoning combined with multimodal sensor fusion for autonomous driving. DriveAgent orchestrates specialized agents operating on camera, Light Detection and Ranging (LiDAR), Inertial…
Vision-Language-Action (VLA) models achieve strong generalization in robotic manipulation but remain largely reactive and 2D-centric, making them unreliable in tasks that require precise 3D reasoning. We propose GeoPredict, a geometry-aware VLA framework that augments a continuous-action policy with
We introduce DriveAgent, a modular multi-agent autonomous driving framework that leverages large language model (LLM) reasoning combined with multimodal sensor fusion for autonomous driving. DriveAgent orchestrates specialized agents operating on camera, Light Detection and Ranging (LiDAR), Inertial
Low-Dimension-to-High-Dimension (LDHD) generalization, a subset of Out-of-Distribution (OOD) generalization, involves training on a low-dimensional subspace and testing in a high-dimensional space. Assuming instances are generated from latent variables reflecting problem scale, LDHD generalization c…
Matrix graph signals, which are associated with two factor graphs, are ubiquitous in daily life, such as time-varying physical signals in sensor networks and rating matrices in recommendation systems. In practice, due to the row-wise and column-wise smoothness, they are modeled as bandlimited (BL) g…
Autonomous learning of dexterous, long-horizon robotic skills has been a longstanding pursuit of embodied AI. Recent advances in robotic reinforcement learning (RL) have demonstrated remarkable performance and robustness in real-world visuomotor control tasks. However, applying RL in the real world
Accurate estimation of the in-hand pose of an object based on its CAD model is crucial in both industrial applications and everyday tasks—ranging from positioning workpieces and assembling components to seamlessly inserting devices like USB connectors. While existing methods often rely on regression…
Virtual network embedding (VNE) is an essential resource allocation task in network virtualization, aiming to map virtual network requests (VNRs) onto physical infrastructure. Reinforcement learning (RL) has recently emerged as a promising solution to this problem. However, existing RL-based VNE met…
Object rearrangement, a fundamental challenge in robotics, demands versatile strategies to handle diverse objects, configurations, and functional needs. To achieve this, the AI robot needs to learn functional rearrangement priors to specify precise goals that meet the functional requirements. Previo
Optimization and sampling based algorithms are two branches of methods in machine learning, while existing safe reinforcement learning (RL) algorithms are mainly based on optimization, it is still unclear whether sampling based methods can lead to desirable performance with safe policy. This paper f…
We study a typical optimization model where the optimization variable is composed of multiple probability distributions. Though the model appears frequently in practice, such as for policy problems, it lacks specific analysis in the general setting. For this optimization problem, we propose a new s…
Creating visually pleasing stylized ink paintings from 3D models is a challenge in robotic manipulation. We propose a semi-automatic framework that can extract expressive strokes from 3D models and draw them in oriental ink painting styles by using a robotic arm. The framework consists of a simulati
Safe reinforcement learning considers practical scenarios that maximize the return while satisfying safety constraints. Current algorithms, which suffer from training oscillations or approximation errors, still struggle to update the policy efficiently with precise constraint satisfaction. In this a…
Offline safe reinforcement learning (RL) algorithms promise to learn policies that satisfy safety constraints directly in offline datasets without interacting with the environment. This arrangement is particularly important in scenarios with high sampling costs and potential dangers, such as autonom…
Safe reinforcement learning (RL) studies problems where an intelligent agent has to not only maximize reward but also avoid exploring unsafe areas. In this study, we propose CUP, a novel policy optimization method based on Constrained Update Projection framework that enjoys rigorous safety guarantee…
Safe reinforcement learning aims to learn the optimal policy while satisfying safety constraints, which is essential in real-world applications. However, current algorithms still struggle for efficient policy updates with hard constraint satisfaction. In this paper, we propose Penalized Proximal Pol…
Improving sample efficiency has been a longstanding goal in reinforcement learning. This paper proposes VRMPO algorithm: a sample efficient policy gradient method with stochastic mirror descent. In VRMPO, a novel variance-reduced policy gradient estimator is presented to improve sample efficiency. W…
We study the convergence of Expected Sarsa(λ) with function approximation. We show that with off-line es- timate (multi-step bootstrapping) to ExpectedSarsa(λ) is unstable for off-policy learning. Furthermore, based on convex-concave saddle-point framework, we propose a con- vergent Gradient Expecte…
The policy-based reinforcement learning (RL) can be considered as maximization of its objective. However, due to the inherent non-concavity of its objective, the policy gradient method to a first-order stationary point (FOSP) cannot guar- antee a maximal point. A FOSP can be a minimal or even a sadd…
Acquiring realistic texture details for 3D models is important in 3D reconstruction. However, the existence of geometric errors, caused by noisy RGB-D sensor data, always makes the color images cannot be accurately aligned onto reconstructed 3D models. In this paper, we propose a global-to-local cor…
A perennial problem in structure from motion (SfM) is visual ambiguity posed by repetitive structures. Recent disambiguating algorithms infer ambiguities mainly via explicit background context, thus face limitations in highly ambiguous scenes which are visually indistinguishable. Instead of analyzin…