DEEP Robotics Humanoids Join Traffic Police at Hangzhou Marathon

DEEP Robotics’ humanoids joined traffic-management operations at the Hangzhou Marathon on November 1, taking on a supporting role around the city’s Huanglong Sports Center.

The machines, known as Hangxing No.2, were developed with local traffic authorities and formed part of a patrol arrangement covering four locations, according to a Global Times report republished by Hangzhou’s official English-language website.

Key Takeaways

Show all

• Hangxing No.2 humanoids supported traffic operations at the November 1 Hangzhou Marathon.
• The company describes duties including patrols, traffic-safety warnings and answering public inquiries.
• The robots use DEEP Robotics’ DR02 platform, which the manufacturer markets for outdoor industrial work.

Humanoids beside the race route

DEEP Robotics shared a video of the deployment on X. The video shows two yellow-and-black humanoids wearing police-style caps at a pedestrian crossing, with runners, onlookers and vehicles nearby.

The report describes a combination of intersection monitoring, preset-route patrols, warnings about traffic violations and public-information services. According to the company, the robots can perform standardized traffic-control gestures and broadcast safety advisories, helping with repetitive roadside work.

The marathon drew 36,000 runners. DEEP Robotics presented the deployment as an opportunity to explore a repeatable model for humanoid support at large races, where crowds and movement patterns change over a concentrated period.

An outdoor role for DR02

The marathon appearance follows DR02’s earlier traffic-assistance testing in rainy conditions in Hangzhou’s West Lake district, which we covered on October 6. That footage showed traffic reminders, pedestrian interaction and obstacle-avoidance testing, with the machines marked as test units.

Hangxing No.2 is based on DR02. On its official product page, DEEP Robotics lists full-body IP66 protection and an operating-temperature range of −20°C to 55°C. The company also describes replaceable limb modules intended to simplify maintenance.

Those design priorities are relevant to roadside work, where a robot must contend with weather and shared public space. They do not, by themselves, establish how reliably it can interpret a crowded crossing or respond to an unusual situation.

The available reporting does not provide intervention counts, accuracy measurements for violation detection or a detailed account of operator control during the event. It also does not establish that the robots independently issued penalties.

The clearest takeaway is the setting: a public event gave DEEP Robotics a chance to put its humanoid traffic-support concept alongside real pedestrian and vehicle flows. Whether that becomes routine deployment will depend on consistent performance and a clear division of responsibility between machines and officers.