This is the implementation of Online Task-Free Continual Generative and Discriminative Learning via Dynamic Cluster Memory

High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization

A collection of online continual learning paper implementations and tricks for computer vision in PyTorch, including our ASER(AAAI-21), SCR(CVPR21-W) and survey (Neurocomputing).

[NeurIPS 2023] A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm

A paper list of our recent survey on continual learning, and other useful resources in this field.

Codebase for "Online Continual Learning with Maximally Interfered Retrieval"

CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).

Pytorch implementation of Self-Attention Generative Adversarial Networks (SAGAN)

WayFASTER: a Self-Supervised Traversability Prediction for Increased Navigation Awareness

A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related webs…

Reproduction code of paper "World Model-based Perception for Visual Legged Locomotion"

[ICRA 2024]: Train your parkour robot in less than 20 hours.

Learning-based locomotion control from OpenRobotLab, including Hybrid Internal Model & H-Infinity Locomotion Control

Code for training locomotion policies with RL

Code for "Temporal Difference Learning for Model Predictive Control"

[CVPR 2022] Codebase for "Coupling Vision and Proprioception for Navigation of Legged Robots"

Official implementation of "Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation" (RSS 2022)

Learned Perceptive Forward Dynamics Model

Code for our RSS'21 paper: "Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Control"

Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modeling

Chance-Constrained MPC simulation for quadrupedal robots navigating uneven terrains and handling random payloads.

Multi/Single UAV(unmanned aerial vehicle) path planning based on deep reinforcement learning

Official code repository for "Integrating Predictive Motion Uncertainties with Distributionally Robust Risk-Aware Control for Safe Robot Navigation in Crowds"

Code for the IEEE Robotics and Automation Letters paper titled "Multi-Modal MPPI and Active Inference for Reactive Task and Motion Planning"

Adaptive Risk Tendency Implicit Quantile Network for Drone Navigation under Partial Observability.