Understand this story
On October 24, 2026, DEEP Robotics concentratedly announced five research results centered on its self-developed embodied brain, DEEPRobotics-Brain: the world model DR-WM-1.0, the embodied foundation model DR-VLA-2.0, the embodied agent DR-Agent, the policy optimization framework DR-APO, and the data closed-loop platform DR-Benchmark, covering the full-chain technology of the embodied brain. The related research was advanced separately by DEEP Robotics in collaboration with seven universities including MIT, Tsinghua University, and Zhejiang University. Among them, DR-APO raised the NavDP simulation success rate from 70.33% to 89.55% in post-training for embodied visual navigation; DR-Benchmark completed 833.6 hours and 3,294.7 kilometers of real-world operation data collection based on the Lynx M20 wheeled-legged robot. On October 26, a Shangguan News report added that DR-APO also raised the Lynx M20's real-world navigation success rate from 25% to 65%. There are currently no further developments.
AI-generated from public reports
Latest development · Report
DEEP Robotics releases five embodied brain achievements including DR-WM-1.0 and DR-VLA-2.0Developments
1 confirmed developments
DEEP Robotics intensively releases five research results on embodied brains
Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 26
Shanghai Observer
DEEP Robotics releases five embodied brain achievements including DR-WM-1.0 and DR-VLA-2.0
DEEP Robotics intensively released five embodied brain achievements: the world model DR-WM-1.0, the embodied foundation model DR-VLA-2.0, the embodied agent DR-Agent, the policy optimization framework DR-APO, and the data closed-loop platform DR-Benchmark. In post-training for embodied visual navigation, DR-APO raised the NavDP simulation success rate from 70.33% to 89.55%, and raised the Lynx M20's real-world navigation success rate from 25% to 65%. The core dataset of DR-Benchmark, LynxScenes, is based on a cumulative 833.6 hours and 3,294.7 kilometers of real-world operation data collected by the Lynx M20.
Oct 24
ZhidxRelated discussion
Zhidx joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Intelligent Manufacturing Network
DEEP Robotics releases five research results on embodied brain
DEEP Robotics concentratedly announced five results around its self-developed embodied brain DEEPRobotics-Brain: the world model DR-WM-1.0, the embodied foundation model DR-VLA-2.0, the embodied agent DR-Agent, the policy optimization framework DR-APO, and the data closed-loop platform DR-Benchmark, covering the full technical chain of the embodied brain. These studies are respectively advanced by DEEP Robotics in collaboration with seven universities including MIT, Tsinghua University, and Zhejiang University. Among them, DR-APO raised the NavDP simulation success rate from 70.33% to 89.55% in embodied visual navigation post-training, and DR-Benchmark completed 833.6 hours and 3,294.7 kilometers of real-world operation data collection based on the Lynx M20 wheeled-legged robot.
Heat trend for this story
- Current
- 9
- Period peak
- 16 Oct 26 10:00
- 24-hour change
- —
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.