Robots are improving their autonomy with minimal human supervision. However, auditable actions, transparent decision processes, and new human-robot interaction models are still missing requirements to achieve extended robot autonomy. To tackle these challenges, we propose RODEO (RObotic DEcentralized Organization), a blockchain-based framework that integrates trust and accountability mechanisms for robots. This paper formalizes Decentralized Autonomous Organizations (DAOs) for service robots. First, it provides a ROS-ETH bridge between the DAO and the robots. Second, it offers templates that enable organizations (e.g., companies, universities) to integrate service robots into their operations. Third, it provides proof-verification mechanisms that allow robot actions to be auditable. In our experimental setup, a mobile robot was deployed as a trash collector in a lab scenario. The robot collects trash and uses a smart bin to sort and dispose of it correctly. Then, the robot submits a proof of the successful operation and is compensated in DAO tokens. Finally, the robot re-invests the acquired funds to purchase battery charging services. Data collected in a three day experiment show that the robot doubled its income and reinvested funds to extend its operating time. The proof validation times of approximately one minute ensured verifiable task execution, while the accumulated robot income successfully funded up to 88 hours of future autonomous operation. The results of this research give insights about how robots and organizations can coordinate tasks and payments with auditable execution proofs and on-chain settlement.
Figures & tables
Fig. 1 : Illustration of the interaction between humans, robots, and organizations by using blockchain-based SCs and proof-verification mechanisms . The proposed framework is composed of: A) DAO bridge: an interface that gives organizations, humans, and robots a common tool to publish tasks and services, receive assignments, and manage rewards. B) Blockchain network: a platform that defines the rules of the operation of the organization, and C) Verification oracle: proof-verification entity for actions performed in the physical world
Fig. 2 : Cleaning task scenario. The figure depicts the physical and cyber sections of this use case. The left section shows the physical space, where a mobile robot equipped with a robotic arm performs the waste collection sequence (steps 1–5) followed by the battery charging process (steps 6 and 7). The right section represents the cyber space, showing the deployment of smart contracts on the public Sepolia testnet and the operation of the verification oracle implemented on a local server connected to the Web3 interface.
Fig. 3 : Sequence diagram of the on-chain workflow across ServiceManager.sol , TaskManager.sol , Organization.sol , and the proof- verification oracle.
Fig. 4 : Completion times (in minutes) for task and proof creation. Bar plots show the median completion times for the cleaning (blue) and charging (green) tasks. Light colors show the median time of proof creation after the corresponding task was completed.
Fig. 5 : Balance of the robot’s wallet (in IEC) from September 10th - 12th 2025. In the figure, green diamonds represent transactions from the organization to the robot as reward for successful execution of the cleaning task. Red diamonds represent the purchase of electricity for battery charging. Finally, the blue line represents the electricity price in €/kWh for the duration of the experiment.
Fig. 6 : Daily extended operating hours funded by the robot’s task earnings. Each bar represents the autonomy gained from that specific end-of-day balance, summing to a total of 11 charges (88 hours) over the three-day period.
Proposed governance framework for autonomous robotic systems, introducing a three-layer compliance architecture (ARC) instantiated through model safety validation, cognitive certification benchmarks, and operational authorization standards.
Robotics foundation models (RFMs) are making general-purpose robots increasingly practical for factory deployments. While RFM serving systems are central to this vision, existing systems are largely shaped by a single-robot, single-model assumption: inference is treated as an edge-computing problem handled by an on-robot or dedicated nearby GPU, and the serving objective is to minimize the latency of a single action model. In this paper, we propose ROSA, an RFM serving system for robot factories designed around three key principles. First, ROSA adopts shared GPU-pool serving, allowing a fleet of robots to access powerful server-class GPUs over the network in order to improve inference performance, battery duration, and GPU utilization. Second, ROSA provides a robotics-aware programming abstraction and system design that supports multi-model pipelines, per-task performance requirements, and failure handling. Third, ROSA uses factory-objective-driven scheduling to maximize SLO-qualified factory productivity rather than minimizing individual request latency. We implement ROSA on top of Ray Serve for distributed orchestration, with vLLM, PyTorch, and JAX as model-serving backends, and evaluate it on both real robots and synthetic large-scale workloads. The results show that ROSA improves factory productivity by up to 12.06x over conventional dedicated serving systems.
Robot agents must connect their intended actions to observed outcomes while retaining the context needed to revise their choices over repeated attempts. Existing interfaces often leave these choices inside predefined tools or require agents to manage detailed execution code and its growing history. We introduce RobotUse, a robot agent harness that organizes computation, context, and decisions around specifying and revising physical actions. Agents visually select targets and poses, while the backend handles geometry, motion planning, and control. Subagents retain detailed interactions within each subgoal and return the information needed for subsequent decisions. Continual harnessing lets agents learn from execution by updating a persistent playbook. On RoboLab, RobotUse achieves 45% task success, outperforming CaP-X by 6.7 percentage points while maintaining compact decision contexts and reducing reliance on predefined action abstractions. Furthermore, we show that RobotUse learns from real-world execution despite imperfect feedback and transfers what it learns to subsequent tasks. Project page is available at https://robotuse-team.github.io/.