Open-television: Teleoperation with immersive active visual feedback
Teleoperation serves as a powerful method for collecting on-robot data essential for robot
learning from demonstrations. The intuitiveness and ease of use of the teleoperation system …
learning from demonstrations. The intuitiveness and ease of use of the teleoperation system …
Tinyvla: Towards fast, data-efficient vision-language-action models for robotic manipulation
Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor
control and instruction comprehension through end-to-end learning processes. However …
control and instruction comprehension through end-to-end learning processes. However …
Policy adaptation via language optimization: Decomposing tasks for few-shot imitation
Learned language-conditioned robot policies often struggle to effectively adapt to new real-
world tasks even when pre-trained across a diverse set of instructions. We propose a novel …
world tasks even when pre-trained across a diverse set of instructions. We propose a novel …
A survey on enhancing reinforcement learning in complex environments: Insights from human and llm feedback
AR Laleh, MN Ahmadabadi - arXiv preprint arXiv:2411.13410, 2024 - arxiv.org
Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating
remarkable potential in tackling real-world challenges. Despite its promising prospects, this …
remarkable potential in tackling real-world challenges. Despite its promising prospects, this …
View: Visual imitation learning with waypoints
Robots can use Visual Imitation Learning (VIL) to learn everyday tasks from video
demonstrations. However, translating visual observations into actionable robot policies is …
demonstrations. However, translating visual observations into actionable robot policies is …
FLAIR: Feeding via Long-horizon AcquIsition of Realistic dishes
RK Jenamani, P Sundaresan, M Sakr… - arXiv preprint arXiv …, 2024 - arxiv.org
Robot-assisted feeding has the potential to improve the quality of life for individuals with
mobility limitations who are unable to feed themselves independently. However, there exists …
mobility limitations who are unable to feed themselves independently. However, there exists …
Words2contact: Identifying support contacts from verbal instructions using foundation models
This paper presents Words2Contact, a language-guided multi-contact placement pipeline
leveraging large language models and vision language models. Our method is a key …
leveraging large language models and vision language models. Our method is a key …
The Ingredients for Robotic Diffusion Transformers
In recent years roboticists have achieved remarkable progress in solving increasingly
general tasks on dexterous robotic hardware by leveraging high capacity Transformer …
general tasks on dexterous robotic hardware by leveraging high capacity Transformer …
Autonomous interactive correction MLLM for robust robotic manipulation
The ability to reflect on and correct failures is crucial for robotic systems to interact stably with
real-life objects. Observing the generalization and reasoning capabilities of Multimodal …
real-life objects. Observing the generalization and reasoning capabilities of Multimodal …
InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation
Bimanual manipulation presents unique challenges compared to unimanual tasks due to the
complexity of coordinating two robotic arms. In this paper, we introduce InterACT: Inter …
complexity of coordinating two robotic arms. In this paper, we introduce InterACT: Inter …