Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

By Zipeng Fu, Tony Zhao, Chelsea Finn. arXiv.org, 2024

712 citations recorded by the source corpus.

Imitation learning from human demonstrations has shown impressive performance in robotics. However, most results focus on table-top manipulation, lacking the mobility and dexterity necessary for generally useful tasks. In this work, we develop a system for imitating mobile manipulation tasks that are bimanual and require whole-body control. We first present Mobile ALOHA, a low-cost and whole-body teleoperation system for data collection. It augments the ALOHA system with a mobile base, and a whole-body teleoperation interface. Using data collected with Mobile ALOHA, we then perform supervised behavior cloning and find that co-training with existing static ALOHA datasets boosts performance on mobile manipulation tasks. With 50 demonstrations for each task, co-training can increase success rates by up to 90%, allowing Mobile ALOHA to autonomously complete complex mobile manipulation tasks such as sauteing and serving a piece of shrimp, opening a two-door wall cabinet to store heavy cooking pots, calling and entering an elevator, and lightly rinsing a used pan using a kitchen faucet. Project website: https://mobile-aloha.github.io

Subfields: Control and Systems Engineering, Rehabilitation, Social Psychology

View Paper: https://www.semanticscholar.org/paper/fc3819a50705fc3cf90ab92f2a206b858fef3b19

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

In Rehabilitation

In Social Psychology

Citations in the corpus

RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation (2025, neutral): “Many task-specific policy architectures [36, 17, 43, 8, 12, 7, 24, 36, 22, 23, 38, 37] achieve strong single-task performance but struggle to transfer across embodiments.”
Robotic Control via Embodied Chain-of-Thought Reasoning (2024, positive): “Robotic policies trained end-to-end for outputting raw low-level actions in response to observations provide a powerful and appealing learning-based approach to robotic control, obviating the need for complex sensing and control stacks [1, 2, 3].”
π0: A Vision-Language-Action Flow Model for General Robot Control (2024, positive): “…action spaces to accomplish a wide variety of tasks. of more complex and dexterous behaviors, such as tying shoelaces [58] or cooking shrimp [17], we show that our framework can learn very long tasks, sometimes tens of minutes in length, for behaviors that combine both physical dexterity…”
HumanPlus: Humanoid Shadowing and Imitation from Humans (2024, background): “Imitation learning has shown great success on learning autonomous robot skills given demonstrations on a wide range of tasks [5, 11, 15, 25, 104].”
RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation (2024, positive): “To evaluate the model on the hardware, we choose the ALOHA dual-arm robot as our target robot since it is one of the most representative dual-arm robots and is suitable for collecting human demonstration data via teleoperation (Zhao et al., 2023; Fu et al., 2024; Aldaco et al., 2024).”
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset (2024, positive): “The success of transformer models [58] in natural language processing and computer vision motivated a number of recent works that collected large-scale demonstration datasets and trained transformer-based policies on them [2, 16, 25, 38, 39, 42, 49, 51, 65, 67].”
TinyVLA: Toward Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation (2024, positive): “These models run efﬁciently, Vision-language models for robot learning: Robot learning [9], [18], [19], [20], [21] is an crucial topic in the robotics.”
Octo: An Open-Source Generalist Robot Policy (2024, background): “…including the use of denoising diffusion objectives [34] for action decoding [17, 31, 85], the prediction of “action chunks”, i.e., sequences of future actions [98, 17, 28], and model layouts and learning rate schedules inspired by the literature on scalable vision transformer training [22, 97].”
Open-TeleVision: Teleoperation with Immersive Active Visual Feedback (2024, neutral): “If we distinguish the existing work with sources of demonstrations, we can classify them into learning from real-robot expert data [14, 10, 12, 59, 60, 61, 62, 50, 63, 1, 64, 51, 65], learning from play data [66, 67, 68], and learning from human demonstrations [67, 69, 70, 71, 72, 73, 74, 56].”
Evaluating Real-World Robot Manipulation Policies in Simulation (2024, positive): “Much recent work in robotic manipulation has demonstrated impressive tasks that go beyond rigid object manipulation [20, 10, 33].”
Aligning Cyber Space With Physical World: A Comprehensive Survey on Embodied AI (2024, neutral): “Mobile ALOHA[221]enablesdatacollectionforfull-bodymobile manipulationtasks.”
Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots (2024, background): “While recent advancements in leader-follower (i.e. puppetting) devices such as ALOHA [53, 15] and GELLO [46] offer promise with intuitive and low-cost interfaces, their reliance on real robots during data collection limits the type and number of environments the system can gain access to for…”
OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning (2024, background): “The embodiment alignment between humanoids and humans not only makes the humanoid a potential generalist platform but also enables the seamless integration of human cognitive skills for scalable data collections [2, 3, 4, 5].”