Related papers: PDP: Physics-Based Character Animation via Diffusi…

Human image animation aims to generate a human motion video from the inputs of a reference human image and a target motion video. Current diffusion-based image animation systems exhibit high precision in transferring human identity into…

We present a method for reproducing complex multi-character interactions for physically simulated humanoid characters using deep reinforcement learning. Our method learns control policies for characters that imitate not only individual…

We propose a two-stage framework for motion in-betweening that combines diffusion-based motion generation with physics-based character adaptation. In Stage 1, a character-agnostic diffusion model synthesizes transitions from sparse…

Reinforcement learning (RL) has achieved strong performance in robotic control; however, state-of-the-art policy learning methods, such as actor-critic methods, still suffer from high sample complexity and often produce physically…

Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies overlook one or both. They typically rely on 2D visual observations and backbones pretrained…

Nature evolves creatures with a high complexity of morphological and behavioral intelligence, meanwhile computational methods lag in approaching that diversity and efficacy. Co-optimization of artificial creatures' morphology and control in…

Visuomotor policy learning has witnessed substantial progress in robotic manipulation, with recent approaches predominantly relying on generative models to model the action distribution. However, these methods often overlook the critical…

Motion tracking has been an important technique for imitating human-like movement from large-scale datasets in physics-based motion synthesis. However, existing approaches focus on tracking either single character or a particular type of…

Diffusion policies (DPs) achieve state-of-the-art performance on complex manipulation tasks by learning from large-scale demonstration datasets, often spanning multiple embodiments and environments. However, they cannot guarantee safe…

Human-level contact-rich manipulation relies on the distinct roles of two key modalities: vision provides spatially rich but temporally slow global context, while force sensing captures rapid, high-frequency local contact dynamics.…

Diffusion-based models have achieved notable empirical successes in reinforcement learning (RL) due to their expressiveness in modeling complex distributions. Despite existing methods being promising, the key challenge of extending existing…

Scene-aware motion synthesis has been widely researched recently due to its numerous applications. Prevailing methods rely heavily on paired motion-scene data, while it is difficult to generalize to diverse scenes when trained only on a few…

Recent work has demonstrated the potential of diffusion models in robot bimanual skill learning. However, existing methods ignore the learning of posture-dependent task features, which are crucial for adapting dual-arm configurations to…

Diffusion policies are conditional diffusion models that learn robot action distributions conditioned on the robot and environment state. They have recently shown to outperform both deterministic and alternative action distribution learning…

While Reinforcement Learning can achieve impressive results for complex tasks, the learned policies are generally prone to fail in downstream tasks with even minor model mismatch or unexpected perturbations. Recent works have demonstrated…

Transferring reinforcement learning policies trained in physics simulation to the real hardware remains a challenge, known as the "sim-to-real" gap. Domain randomization is a simple yet effective technique to address dynamics discrepancies…

Diffusion policy has demonstrated promising performance in the field of robotic manipulation. However, its effectiveness has been primarily limited in short-horizon tasks, and its performance significantly degrades in the presence of image…

Diffusion-based models for robotic control, including vision-language-action (VLA) and vision-action (VA) policies, have demonstrated significant capabilities. Yet their advancement is constrained by the high cost of acquiring large-scale…

With the great success of diffusion models (DMs) in generating realistic synthetic vision data, many researchers have investigated their potential in decision-making and control. Most of these works utilized DMs to sample directly from the…

Deep reinforcement learning (RL) policies, although optimal in terms of task rewards, may not align with the personal preferences of human users. To ensure this alignment, a naive solution would be to retrain the agent using a reward…