Chronos Policy: Learning Robot Policies on Physical Time
Overview
Chronos Policy integrates physical time into robot learning using time-aware encodings, enhancing performance on dynamic and multisensory tasks while improving robustness to timing changes. It enables asynchronous data learning without fixed temporal grids. Latest research shows improved results in simulation and real-world experiments. Latest: Chronos Policy improves performance on dynamic tasks and multisensory tasks by explicitly incorporating physical time into policy learning. Latest: arXiv:2610.13929v1
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsChronos Policy: Learning Robot Policies on Physical Time
This research proposes Chronos Policy, which explicitly incorporates physical time into robot policy learning by using time-aware rotary positional encodings (time-aware RoPE). The method improves performance on dynamic and multisensory tasks while maintaining robustness to changes in sensing and inference timing.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).