Keeping Jerk in Check: Jointly Trained Perception-Gated Experts for Smooth Terrain Transitions
Overview
This research presents CTS-MoE, a multi-task reinforcement learning framework that jointly trains a perception-gated dense mixture-of-experts actor with task-specific critics to enable smooth transitions across discontinuous terrain. The approach uses soft routing to compose expert knowledge continuously and transfers composition from privileged terrain information to onboard depth for deployment without labels. Evaluated on a Unitree Go1, the policy achieves 93.3% connected-course success compared to 73.3% and 53.3% for hierarchical and DAgger-distilled baselines, reduces mean action jerk by approximately one-third, and completes an extended outdoor course in all 10 trials across four terrain types.
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · trials completed: 10 other · reported trials
“ourse success to 93.3% from 73.3% and 53.3%, lowers mean action jerk by about a third across the course, and avoids the switching transient that hard selection introduces at boundaries. On a Unitree Go1, it completes an extended outdoor course in 10/10 trials and transfers to four outdoor terrain types. Project Website: https://cts-moe.github.io/ .”
Exact source · revision 1Source owner not reported
Reported quantity · trials total: 10 other · reported trials
“ourse success to 93.3% from 73.3% and 53.3%, lowers mean action jerk by about a third across the course, and avoids the switching transient that hard selection introduces at boundaries. On a Unitree Go1, it completes an extended outdoor course in 10/10 trials and transfers to four outdoor terrain types. Project Website: https://cts-moe.github.io/ .”
Exact source · revision 1Source owner not reported
Reported quantity · terrain types transferred: 4 other · Basis not reported
“ourse success to 93.3% from 73.3% and 53.3%, lowers mean action jerk by about a third across the course, and avoids the switching transient that hard selection introduces at boundaries. On a Unitree Go1, it completes an extended outdoor course in 10/10 trials and transfers to four outdoor terrain types. Project Website: https://cts-moe.github.io/ .”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalKeeping Jerk in Check: Jointly Trained Perception-Gated Experts for Smooth Terrain Transitions
This research presents CTS-MoE, a multi-task reinforcement learning framework that jointly trains a perception-gated dense mixture-of-experts actor with task-specific critics to enable smooth transitions across discontinuous terrain. The approach uses soft routing to compose expert knowledge continuously and transfers composition from privileged terrain information to onboard depth for deployment without labels. Evaluated on a Unitree Go1, the policy achieves 93.3% connected-course success compared to 73.3% and 53.3% for hierarchical and DAgger-distilled baselines, reduces mean action jerk by approximately one-third, and completes an extended outdoor course in all 10 trials across four terrain types.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).