Open Source
Successive Convexification in Learned World Models for Safe Offline Planning
arXiv cs.RO0 views
arXiv:2611.19466v1 Announce Type: cross 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.
Source:https://arxiv.org/abs/2611.19466PreviousAcousticBEV: Acoustic BEV Object Localization for Intelligent VehiclesNextRepresenting Differential Inclusions as Monads: A Framework for Compositional Controller Synthesis
Related posts
GOOSELoc: A Multimodal Benchmark for Ground-to-Aerial Localization in Unstructured Off-Road Terrain
0arXiv cs.RO
Linglong Agent Service: A Runtime for Centralized Agent Reasoning and Distributed Execution
0arXiv cs.RO
WiTac: Wrist-Informed Tactile Representations for Contact-Rich Manipulation
0arXiv cs.RO

Backup imutável de RDS com cofre logicamente isolado: o que PCI DSS e ISO 27001 pedem e como provar
0dev.to AWS
Show HN: NetDiag self-hosted network inventory and diagnostics
0Hacker News Show
Show HN: Map showing if GTA 6 is out in your country
0Hacker News Show