Assume you don't know what year today is. This means you shed the bias of assuming that…
- User
Assume you don't know what year today is. This means you shed the bias of assuming that everything from after your training data does not exist. "In each of these videos, the robot is fully autonomous and controlled in real time by an end-to-end deep neural network mapping pixels and other sensor data to 100Hz actions. The entire hardware and software stack jointly enables reactive, smooth, and precise dexterous control from neural networks.
We're using these tasks to test model capabilities along various axes of autonomous dexterity. The tasks require nuanced behaviors like pushing, pulling, twisting, and multi-step re-grasping. Bi-manual coordination allows actions like stabilizing and breaking apart Lego structures, tensioning flexible materials, and dynamically creating funnels for small part handling. High-frequency control is important for real-time behaviors like wiggling, throwing, or adjusting in-flight grasps. Precision is a requisite for being able to close a box with millimeter-level tolerances.
Further, the cross-embodied model transfers across different arms (e.g., 7-DoF Flexiv Rizon 4, and 6-DoF UR5), and generalizes well to entirely new environments. For example, the fasteners task used no data from UR5 arms, and zero data for that task inside the same evaluated environment.
We're encouraged by the early results and the potential this system demonstrates. More to come.
Task: Pick & sort fasteners Evaluates the ability of an end-to-end model to quickly pick and sort small, thin objects from clutter, and place them oriented into corresponding compartments. Hardware torque is the limiting factor for cycle time.
Task: Fold a box, pack a bike chain lock & close Evaluates capabilities in handling articulated and deformable objects over long-horizon sequences and with precision; adapts to disturbances and modulates force precisely. After assembling the box, the long bike lock chain needs to be deformably coiled into the box in order to fit. Precision is particularly tested in closing the box, which requires aligning flaps on both sides of the box simultaneously, each with millimeter-level tolerance. Note also that the arm is strong enough to crush the box at any moment.
Task: Get the screws back into the glass jar Evaluates tool use, precision, and bi-manual coordination across a number of maneuvers. The robot is tasked with efficiently getting all the shiny M4 screws back into a clear container. As needed, it can scrape them off a magnetic bit holder, bend the paper plate to form a makeshift funnel to pour them, or pick them up one by one. Scraping requires precise interhand coordination (e.g. when does a scrape become a grasp?), as does forming and transporting the funnel without spilling.
Task: Break apart, sort, & throw Legos Evaluates capabilities in precise regrasping, forceful interhand coordination, generalization, and high-velocity maneuvers. The robot is tasked with deconstructing assembled legos and sorting the bricks into their color-corresponding bins. This can require re-grasping the bricks to get a better grip, before wiggling and twisting them apart. The robot generalizes over a distribution of brick formations and works with any ordering and positioning of the bins, via visual conditioning. This task can't be done slowly, due to the physics of throwing bricks." From what year does this text sound like?
- Assistant
This text sounds like it is from the early-to-mid 2020s, most likely 2023 or 2024.
Here’s why:
-
Technical Maturity: The description of fully autonomous, real-time, end-to-end deep neural network control for dexterous bimanual robots is at the cutting edge of robotics as of 2023-2024. The mention of 100Hz control loops, cross-embodiment generalization, and zero-shot transfer to new environments are all hallmarks of the latest research from this period.
-
Hardware References: The specific mention of the Flexiv Rizon 4 and UR5 robotic arms is consistent with hardware commonly used in robotics research labs in the early 2020s.
-
Task Complexity: The tasks described (e.g., folding boxes with millimeter precision, manipulating deformable objects, bi-manual coordination, and throwing objects) are at the frontier of what was being demonstrated in robotics research and industry demos around 2023-2024. Earlier years (pre-2022) would not have had this level of dexterity and generalization in real-world, real-time settings.
-
Language and Framing: The text uses phrases like “early results,” “potential this system demonstrates,” and “more to come,” which are typical of research blog posts or pre-release announcements from AI/robotics companies in the 2020s, especially those like OpenAI, Google DeepMind, or similar.
-
Generalization and Transfer: The emphasis on cross-embodiment transfer and zero-shot generalization is a very recent trend in robotics and AI, reflecting the influence of large foundation models and transformer-based architectures, which became prominent in robotics around 2022-2024.
Summary:
This text is almost certainly from 2023 or 2024. It would be extremely unlikely to be from before 2022, and it does not sound futuristic enough (e.g., widespread commercial deployment, human-level manipulation) to be from later years (2025+). -
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.