Humanoid AI connects walking and object handling without demonstrations of complete task sequences
Overview
A research team from Seoul National University has developed RISE, a vision-language-action framework that allows humanoid robots to learn locomotion and object manipulation separately but jointly within a single model. Validated on simulation and the Unitree G1 robot (43 DoF), RISE achieved an average success rate of 87.3% in simulation and 50.0% on hardware for multistage tasks, outperforming a GR00T-based baseline. The system uses a meta-controller to coordinate specialized experts and signals from expert weights to determine task transitions, reducing the need to collect continuous demonstrations of complex sequences.
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
1 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Environment: simulation
“tistep tasks involving transitions between the two behaviors, and validated the framework in both simulation and experiments using a real humanoid robot, the Unitree G1. The research was accepted for the IEEE/RSJ International Conference on Intelligent Robots and Systems ( IROS 2026 ). Video demonstrating a humanoid vision-language-action (VLA) model trained jointly on separately collected locomotion and object-manip”
Exact source · revision 2science-x
Reported quantity · Reported success rate: 87.3 percent · Basis not reported · Differing source assertions
“cking up an object, moving again and placing it down. Across all simulation experiments, RISE achieved an average success rate of 87.3%, outperforming the 73.6% achieved by a GR00T-based baseline with a single-expert architecture. GR00T is a general-purpose foundation model for humanoid robots released by NVIDIA. In experiments using a real Unitree G1 robot, the system performed locomotion and manipulation tasks cons”
Exact source · revision 2science-x
Reported quantity · Reported success rate: 50 percent · Basis not reported · Differing source assertions
“isting of two stages, four stages and up to five stages. The robot sequentially picked up an object and placed it at another location, then picked up a second object, moved to the target location and placed it down. RISE achieved an average task success rate of 50.0%, 20 percentage points higher than the 30.0% recorded by the GR00T-based baseline. In particular, RISE performed tasks more reliably than the baseline as”
Exact source · revision 2science-x
Reported quantity · degrees of freedom: 43 other · Basis not reported
“n the experiments was equipped with two Dex3-1 robotic hands in addition to its basic whole-body joints, giving it a total of 43 controllable degrees of freedom (DoF). In simulation experiments, the robot was assigned two- to four-stage tasks involving objects such as apples, bottles and cups. These included moving and then picking up an object; picking up an object and then moving and placing it down; and moving, pi”
Exact source · revision 2science-x
Reported quantity · task stages: 2 other · Basis not reported · Differing source assertions
“n the experiments was equipped with two Dex3-1 robotic hands in addition to its basic whole-body joints, giving it a total of 43 controllable degrees of freedom (DoF). In simulation experiments, the robot was assigned two- to four-stage tasks involving objects such as apples, bottles and cups. These included moving and then picking up an object; picking up an object and then moving and placing it down; and moving, pi”
Exact source · revision 2science-x
Reported quantity · task stages: 4 other · Basis not reported · Differing source assertions
“n the experiments was equipped with two Dex3-1 robotic hands in addition to its basic whole-body joints, giving it a total of 43 controllable degrees of freedom (DoF). In simulation experiments, the robot was assigned two- to four-stage tasks involving objects such as apples, bottles and cups. These included moving and then picking up an object; picking up an object and then moving and placing it down; and moving, pi”
Exact source · revision 2science-x
Report timeline
Follow attributed reports and material updates.
- Tech Xplore — RoboticsSignalHumanoid AI connects walking and object handling without demonstrations of complete task sequences
A research team from Seoul National University has developed RISE, a vision-language-action framework that allows humanoid robots to learn locomotion and object manipulation separately but jointly within a single model. Validated on simulation and the Unitree G1 robot (43 DoF), RISE achieved an average success rate of 87.3% in simulation and 50.0% on hardware for multistage tasks, outperforming a GR00T-based baseline. The system uses a meta-controller to coordinate specialized experts and signals from expert weights to determine task transitions, reducing the need to collect continuous demonstrations of complex sequences.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).