cs.LGNov 14, 2026

Successive Convexification in Learned World Models for Safe Offline Planning

Authors: Samuel Younger

Organizations: Department of Aeronautics, Imperial College London, London, UK

Abstract

World models learned from offline data allow an agent to plan without further interaction with the environment, but the sampling-based planners used with them handle safety constraints only by scoring or rejecting sampled action sequences. We instead pose safe planning in the latent space of a learned world model as a successive convex program (SCP), in which a learned discrete-time control barrier function is imposed as a constraint at every step of the horizon. SCP requires smooth dynamics, so we build the networks from smoothed MaxMin activations and spectrally normalised layers, and bound the resulting linearisation error in terms of the Lipschitz bound and the smoothing width. As SCP is a local method, we start it from a sampled plan. On two Safety-Gymnasium navigation tasks with offline data, this planner has fewer violations than MPPI and CEM drawing 128 times as many samples at equal wall-clock time in our main comparison, though not significantly, and earns greater return at longer horizons, and is much safer than SCP without a sampled start. SCP converged more often on Lipschitz-bounded models. Unlike sampling, it also reports at each step whether its plan is a feasible, first-order optimal KKT point of the planning problem in the model, or that no feasible plan was found nearby. Our implementation is publicly available at https://github.com/youngers2006/scwm.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Aug 19, 2026

Reinforced Planning with Latent World Models

Humans solve complex problems by constructing plans and mentally simulating their outcomes with an internal model of the world. Machine learning has made substantial progress in learning world models that predict the consequences of action sequences, yet the procedures used to plan with these models remain largely hand-designed. Most planners rely on fixed search or optimization rules; approaches that learn aspects of search typically imitate a predefined optimizer or use planning to inform an amortized policy, rather improving multi-step plans. We introduce Reinforced Planning, a method that learns the plan-update itself by reinforcing update rules that produce better plans, using gradients propagated through a differentiable world model. We instantiate Reinforced Planning in RP1, which learns a critic over imagined outcomes via temporal-difference learning and a neural plan-improvement operator trained via imagined rollouts with a pretrained world model. RP1 can be trained fully offline without environment interaction; environment episodes are used only for checkpoint selection. Across visual navigation, arm reaching, and robotic manipulation on two world-model backbones, RP1 matches or exceeds existing planners, achieving near-perfect success in several settings while using 1,000×1{,}000\times fewer world-model rollouts than the strongest alternative (CEM) and planning up to 67×67\times faster under concurrent planners inference.
Jun 14, 2026

Pixels to Proofs: Probabilistically-Safe Latent World Model Control via Parallel Conformal Robust MPC

We present SLS^2, a framework for safe feedback motion planning from pixels using robust model predictive control (MPC) in learned latent world models. Our approach trains an action-conditioned joint-embedding world model with compact Markovian latent states, enabling efficient gradient-based trajectory optimization through learned latent dynamics. To enforce safety for the true system despite imperfect latent predictions, we inform a GPU-accelerated system level synthesis (SLS) robust MPC scheme with conformal prediction to obtain calibrated latent error bounds and robust latent-space constraint sets. We further learn and conformalize a latent constraint checker, allowing the SLS planner to impose probabilistic safety constraints during closed-loop execution. We evaluate our method on vision-based control tasks, where it improves both goal-reaching performance and safety over latent world-model and safe-planning baselines.
Nov 15, 2026

SAFER: Navigating the Exploration-Exploitation Dilemma in World-Model-Based Planning for Autonomous Driving

An autonomous vehicle must foresee the consequences of its actions, especially in the rare, time-critical situations where crashes happen. A world model offers this foresight, but only within the coverage of its training data, which poses an exploration-exploitation dilemma. Within this coverage a planner can hardly improve on the data, and beyond it the model's errors mislead it. Logs of competent driving rarely contain the failures that would widen the coverage, and agents that learn from interaction gain them only by failing themselves, without being shown what to do instead. We propose SAFER, a framework that learns offline from failures that others make, judged by an expert, and keeps learning online from its own driving. Offline, partially trained agents and scripted, recoverable perturbations Stage failures in simulation, and an expert Annotates every visited state with its action and value, so that much of what the planner explores is covered before it drives. In planning, a chunked latent world model Foresees the consequences fast enough for real-time use, and a risk-aware sampling-based planner Evaluates candidate maneuvers by their return minus a bounded collision penalty. Online, a loop continuously Refines the model wherever this driving leaves the coverage of the offline data. In closed-loop evaluation against the compared methods, SAFER reaches the highest route completion and reward per step on the CARLA Leaderboard routes, 0.95 and 0.77 from a privileged bird's-eye view, and the highest episode reward in MetaDrive, 53.4 in regular and 49.0 in safety-critical traffic. Project page: https://ys-qu.github.io/safer-website.