The paper reports the first in‑space demonstration of using machine learning‑based warm starts to accelerate trajectory optimization for the Astrobee free‑flying robot on the International Space Station. A neural network is trained to learn the structure of the trajectory generation problem solved by sequential convex programming, and onboard predictions reduce solver iterations by 60% for rotational dynamics and 50% for obstacle‑laden scenarios. This approach enables real‑time trajectory planning while respecting safety constraints on limited flight hardware.
arXiv:2605. 04568v3 Announce Type: replace-cross Abstract: State-of-the-art model-based Reinforcement Learning (RL) approaches either use gradient-free, population-based methods for planning, learned policy networks, or a combination of policy networks and planning.
arXiv:2608.20948v1 Announce Type: cross Abstract: Autonomous flight in unknown cluttered environments is hindered by the computation-quality-memory trilemma of onboard trajectory generation. In this...
arXiv:2604. 12474v3 Announce Type: replace-cross Abstract: In many robotic tasks, agents must traverse a sequence of spatial regions to complete a mission.
The paper presents a permutation‑equivariant neural operator that learns to generate collision‑free, fuel‑efficient trajectories for spacecraft swarms by mapping distributions of initial and target states, as well as obstacle states, to trajectory outputs. The operator is self‑supervised and, when paired with a batched Gauss‑Newton step, enforces exact orbital dynamics and further reduces fuel consumption. Trained on ten spacecraft, the model generalizes zero‑shot to swarms of 1,000 spacecraft and 11,000 obstacles, achieving accuracy comparable to a per‑agent optimal control solver while maintaining collision avoidance.
arXiv:2510. 21874v2 Announce Type: replace-cross Abstract: Unmanned aerial vehicles (UAVs) operating in dynamic wind fields must generate safe and energy-efficient trajectories under physical and environmental constraints.
Second-order cone programs (SOCPs) are a fundamental class of convex optimization problems widely applied across engineering domains. Classical interior-point methods are robust and accurate, but thei...
The paper introduces a curriculum-driven deep reinforcement learning framework for autonomous far-range rocket landing. It uses a three-stage curriculum, critic warm‑up, rehearsal to avoid catastrophic forgetting, and a high‑dimensional observation vector with a full 3×3 rotation matrix. The redesigned reward function bounds per‑step rewards and accumulates progress, yielding a 99.98% success rate over 100,000 episodes, far surpassing the baseline.
arXiv:2605. 26790v3 Announce Type: replace Abstract: Low-thrust trajectory design relies heavily on repeated evaluations of fuel consumption and transfer feasibility, which require expensive optimal control solutions.
arXiv:2607. 07252v1 Announce Type: new Abstract: Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems (CPSs) and robotics.
arXiv:2606. 31291v1 Announce Type: new Abstract: Deep reinforcement learning has the potential to solve attitude control problems more adaptively, precisely, and robustly by handling nonlinear dynamics, uncertainties, and failure cases more effectively than traditional attitude control approaches.
The paper investigates combining Reinforcement Learning (RL) with search-based path planners to accelerate flight trajectory optimization for airliners. An RL agent is trained to generate near‑optimal paths from location and atmospheric data, which then constrain a traditional solver to reduce its search space. Experiments using Airbus performance models show that fuel consumption deviates by less than 1% from an unconstrained solver while computation time improves by up to 50%.
CALOS is a runtime safety layer for quadrotor control that enforces attitude constraints without altering the underlying deep reinforcement learning algorithm. It formulates tilt-angle inequalities and a Lyapunov descent condition into a single quadratic program, solved exactly via active-set enumeration over a three-dimensional torque space. In NVIDIA Isaac Lab trajectory-tracking tasks, CALOS reduces lateral tracking error by 55‑60% compared to an unconstrained Proximal Policy Optimization baseline and eliminates attitude-constraint violations during training.