ARCS: Autonomous Rendezvous and Control Suite
ARCS is an open-source, headless simulator for testing AI controllers, including large language model (LLM) agents, and classical controllers on spacecraft rendezvous with keep-out safety constraints. It models relative motion with the Clohessy-Wiltshire equations, validated against the closed-form solution to sub-millimeter accuracy over one orbit, and simulates one hour of flight in under 0.1 s. A provider-neutral LLM agent interface logs every prompt, response, parse failure, and latency, and a safety-filter wrapper counts its interventions. In the first result, a PD baseline violates the keep-out zone in 100% of 30 obstructed approaches, which motivates safety-filtered autonomy.
- Keep-out violations, PD baseline
- 30/30 obstructed approaches
- Dynamics error vs closed form
- <1 mm over one orbit
- Runtime per simulated hour
- <0.1 s headless
