MIT robot widens one warning to electronics; GPT-4o errs up to 9 of 105 tests
Robot safety commands: MIT robot widens one warning to electronics; GPT-4o errs up to 9 of 105 tests
Researchers from MIT and New York University have developed FLEX, a system that converts single typed corrections into broader avoidance rules for robots.
Source: Robotics — Robot learning news discovery · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S15
Reported numbers
error count
9
Reported trials
View original evidence
adding is required. USF scores 0.64 on add-only tasks and 0.99 on tasks that need add and mask. The tests used seven 9-by-9 grid navigation scenarios , plus simulated five-stage tasks on a seven-degree-of-freedom Franka arm. Isolated Operations Err in 3.8% to 8.6% of 105 Trials Each The paper's appendix reports a reliability test of each operation alone over 105 trials. Add errs in 8.6% of trials (9 of 105), Generali
Open source S8error count
6
Reported trials
View original evidence
ze in 5.7% (6 of 105) and Mask in 3.8% (4 of 105). The errors count both edits applied wrongly and edits wrongly omitted. Two failure cases from the five-stage tasks show what those errors look like. In stage three, an earlier bowl-proximity feature became a spurious correlation that pulled the trajectory toward the bowl until the user typed a command to ignore it. In stage four, the robot behaved correctly with only
Open source S9error count
4
Reported trials
View original evidence
ze in 5.7% (6 of 105) and Mask in 3.8% (4 of 105). The errors count both edits applied wrongly and edits wrongly omitted. Two failure cases from the five-stage tasks show what those errors look like. In stage three, an earlier bowl-proximity feature became a spurious correlation that pulled the trajectory toward the bowl until the user typed a command to ignore it. In stage four, the robot behaved correctly with only
Open source S9trial count
105 trials
Reported trials
View original evidence
adding is required. USF scores 0.64 on add-only tasks and 0.99 on tasks that need add and mask. The tests used seven 9-by-9 grid navigation scenarios , plus simulated five-stage tasks on a seven-degree-of-freedom Franka arm. Isolated Operations Err in 3.8% to 8.6% of 105 Trials Each The paper's appendix reports a reliability test of each operation alone over 105 trials. Add errs in 8.6% of trials (9 of 105), Generali
Open source S8
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
tended consequences (p = .047), using Holm-adjusted Wilcoxon tests. Against MFE, FLEX rated higher on intent understanding (p = .031), while robustness fell short of significance (p = .074). Ease of use and collaborativity showed no significant differences. The authors state the closed-loop study ran in simulation, supported by hardware feasibility checks, and list a closed-loop user study on physical hardware as fut
Open source S15
MIT and New York University researchers have built FLEX, a system that turns one typed correction, such as a warning about spilling coffee on a laptop, into a broader avoidance rule for a robot, and the accompanying paper shows how often that inference goes wrong: each of its three language-model operations erred in 3.8% to 8.6% of isolated trials. The paper is slated for CoRL 2026 , the Conference on Robot Learning,
Open source S2
ze in 5.7% (6 of 105) and Mask in 3.8% (4 of 105). The errors count both edits applied wrongly and edits wrongly omitted. Two failure cases from the five-stage tasks show what those errors look like. In stage three, an earlier bowl-proximity feature became a spurious correlation that pulled the trajectory toward the bowl until the user typed a command to ignore it. In stage four, the robot behaved correctly with only
Open source S9
adding is required. USF scores 0.64 on add-only tasks and 0.99 on tasks that need add and mask. The tests used seven 9-by-9 grid navigation scenarios , plus simulated five-stage tasks on a seven-degree-of-freedom Franka arm. Isolated Operations Err in 3.8% to 8.6% of 105 Trials Each The paper's appendix reports a reliability test of each operation alone over 105 trials. Add errs in 8.6% of trials (9 of 105), Generali
Open source S8
Source：Robotics — Robot learning news discovery · msn.com