首页|Studies from Georgia Institute of Technology Provide New Data on Robotics (Indoo rsim-to-outdoorreal: Learning To Navigate Outdoors Without Any Outdoor Experienc e)
Studies from Georgia Institute of Technology Provide New Data on Robotics (Indoo rsim-to-outdoorreal: Learning To Navigate Outdoors Without Any Outdoor Experienc e)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on Robotics have been pr esented. According to news originating from Atlanta, Georgia, by NewsRx correspo ndents, research stated, "We present IndoorSim-to-OutdoorReal (I2O), an end-to-e nd learned visual navigation approach, trained solely in simulated short-range i ndoor environments, and demonstrate zero-shot sim-to-real transfer to the outdoo rs for long-range navigation on the Spot robot. Our method uses zero real-world experience (indoor or outdoor), and requires the simulator to model no predomina ntly-outdoor phenomenon (sloped grounds, sidewalks, etc)." Financial support for this research came from Apple Scholars in AI/ML PhD Fellow ship.
AtlantaGeorgiaUnited StatesNorth a nd Central AmericaEmerging TechnologiesMachine LearningRobotRoboticsGe orgia Institute of Technology
NETL
NSTL
