Search Results for author:
Found 9 papers, 3 papers with code
ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
This paper presents a novel framework for modeling and conditional generation of 3D articulated objects.
On the Evaluation of Generative Robotic Simulations
For single-task quality, we evaluate the realism of the generated task and the completeness of the generated trajectories using large language models and vision-language models.
Multi-UAV Pursuit-Evasion with Online Planning in Unknown Environments by Deep Reinforcement Learning
Multi-UAV pursuit-evasion, where pursuers aim to capture evaders, poses a key challenge for UAV swarm intelligence.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
Context-Aware Aerial Object Detection: Leveraging Inter-Object and Background Relationships
Additionally, we introduce self-supervised constraints on CLIP Tokens to ensure consistency.
A Dual Curriculum Learning Framework for Multi-UAV Pursuit-Evasion in Diverse Environments
In this work, we introduce a dual curriculum learning framework, named DualCL, which addresses multi-UAV pursuit-evasion in diverse environments and demonstrates zero-shot transfer ability to unseen scenarios.
Feedback RoI Features Improve Aerial Object Detection
Neuroscience studies have shown that the human visual system utilizes high-level feedback information to guide lower-level perception, enabling adaptation to signals of different characteristics.
OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control
In this work, we introduce OmniDrones, an efficient and flexible platform tailored for reinforcement learning in drone control, built on Nvidia's Omniverse Isaac Sim.
Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
A crucial limitation of this framework is that every policy in the pool is optimized w. r. t.
Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games
In comparison with the state-of-the-art RLlib, we empirically demonstrate the unique advantages of Lamarckian on benchmark tests with up to 6000 CPU cores: i) both the sampling efficiency and training speed are doubled when running PPO on Google football game; ii) the training speed is 13 times faster when running PBT+PPO on Pong game.
