AI researchers challenge a robot to ride a skateboard in simulation

Posted on

AI researchers say they’ve created a framework for controlling four-legged robots that promises better energy efficiency and adaptability than more traditional model-based gait control of robotic legs. To demonstrate the robust nature of the framework that adjusts to conditions in real time, AI researchers made the system slip on frictionless surfaces to mimic a banana peel, ride a skateboard, and climb on a bridge while walking on a treadmill. An Nvidia spokesperson told VentureBeat that only the frictionless surface test was conducted in real life because of limits placed on office staff size due to COVID-19. The spokesperson said all other challenges took place in simulation. (Simulations are often used as training data for robotics systems before those systems are used in real life.)

“Our framework learns a controller that can adapt to challenging environmental changes on the fly, including novel scenarios not seen during training. The learned controller is up to 85% more energy-efficient and is more robust compared to baseline methods,” the paper reads. “At inference time, the high-level controller needs only evaluate a small multi-layer neural network, avoiding the use of an expensive model predictive control (MPC) strategy that might otherwise be required to optimize for long-term performance.”

The quadruped model is trained in simulation using a split-belt treadmill with two tracks that can change speed independently. That training in simulation is then transferred to a Laikago robot in the real world. Nvidia released video of simulations and laboratory work Monday, when it also unveiled AI-powered videoconferencing service Maxine and the Omniverse simulated environment for engineers in beta.

A paper detailing the framework for controlling quadruped legs was published a week ago on preprint repository arXiv. AI researchers from Nvidia; Caltech; University of Texas, Austin; and the Vector Institute at the University of Toronto contributed to the


Three boys, 8, approached by men who ask them if they want a ride: University Heights police blotter

Posted on

UNIVERSITY HEIGHTS, Ohio — Enticing children: Wrenford Road

At 5:20 p.m. Sept. 26, three boys, all 8-year-old University Heights residents, were approached by two older males while on the grounds of Gearity School, 2323 Wrenford Road. The men asked the boys if they wanted to go for a ride with them in their car.

The boys declined the offer and fled the area.

The men then drove from the school grounds in what might have been a white Dodge Caliber hatchback. No other information could be gained as the boys each gave police conflicting versions of what had happened. Police were unable to find the vehicle. The detective bureau is investigating.

Grand theft: Milton Road

At 6:25 a.m. Sept. 21, a man, 60, reported that his car had been stolen from his home’s open garage. The car’s key had been left inside the vehicle. The theft occurred sometime after 10:30 p.m. the previous night.

Grand theft: Churchill Boulevard

At 6:30 a.m. Sept. 21, a woman, 73, reported that her SUV had been stolen from her property during the previous evening.

Pedestrian hit by vehicle: Cedarbrook Road

At 1:45 p.m. Sept. 21, a man, 34, went to the police station lobby to report he had been hit while walking by a 59-year-old city employee driving a city vehicle. Police are investigating.

Theft from auto: Kerwin Road

At 7:45 p.m. Sept. 21, a man, 34, reported that tools had been stolen from his vehicle as it was parked on his property.

Grand theft: Silsby Road

At 6:45 a.m. Sept. 22, a man, 32, reported that his car was stolen while it was parked on his property.

Theft: Cedar Road

Just before noon Sept. 22, police were called to Target, 14070 Cedar Road, where a theft was in progress. Police cited a