Search

Trajectory generation is a pivotal task in autonomous driving. Recent studies have introduced the autoregressive paradigm, leveraging the state transition model to approximate future trajectory distributions. This paradigm closely mirrors the real-world trajectory generation process and has achieved notable success. However, its potential is limited by the ineffective representation of realistic trajectories within the redundant state space. To address this limitation, we propose the Kinematic-Driven Generative Model for Realistic Agent Simulation (KiGRAS). Instead of modeling in the state space, KiGRAS factorizes the driving scene into action probability distributions at each time step, providing a compact space to represent realistic driving patterns. By establishing physical causality from actions (cause) to trajectories (effect) through the kinematic model, KiGRAS eliminates massive redundant trajectories. All states derived from actions in the cause space are constrained to be physically feasible. Furthermore, redundant trajectories representing identical action sequences are mapped to the same representation, reflecting their underlying actions. This approach significantly reduces task complexity and ensures physical feasibility. KiGRAS achieves state-of-the-art performance in Waymo's SimAgents Challenge, ranking first on the WOMD leaderboard with significantly fewer parameters than other models. The video documentation is available at \url{https://kigras-mach.github.io/KiGRAS/}.

End-to-End paradigms use a unified framework to implement multi-tasks in an autonomous driving system. Despite simplicity and clarity, the performance of end-to-end autonomous driving methods on sub-tasks is still far behind the single-task methods. Meanwhile, the widely used dense BEV features in previous end-to-end methods make it costly to extend to more modalities or tasks. In this paper, we propose a Sparse query-centric paradigm for end-to-end Autonomous Driving (SparseAD), where the sparse queries completely represent the whole driving scenario across space, time and tasks without any dense BEV representation. Concretely, we design a unified sparse architecture for perception tasks including detection, tracking, and online mapping. Moreover, we revisit motion prediction and planning, and devise a more justifiable motion planner framework. On the challenging nuScenes dataset, SparseAD achieves SOTA full-task performance among end-to-end methods and significantly narrows the performance gap between end-to-end paradigms and single-task methods. Codes will be released soon.

An imperfect-information game is a type of game with asymmetric information. It is more common in life than perfect-information game. Artificial intelligence (AI) in imperfect-information games, such like poker, has made considerable progress and success in recent years. The great success of superhuman poker AI, such as Libratus and Deepstack, attracts researchers to pay attention to poker research. However, the lack of open-source code limits the development of Texas hold'em AI to some extent. This article introduces DecisionHoldem, a high-level AI for heads-up no-limit Texas hold'em with safe depth-limited subgame solving by considering possible ranges of opponent's private hands to reduce the exploitability of the strategy. Experimental results show that DecisionHoldem defeats the strongest openly available agent in heads-up no-limit Texas hold'em poker, namely Slumbot, and a high-level reproduction of Deepstack, viz, Openstack, by more than 730 mbb/h (one-thousandth big blind per round) and 700 mbb/h. Moreover, we release the source codes and tools of DecisionHoldem to promote AI development in imperfect-information games.

In ABO3 perovskites, oxygen octahedron rotations are common structural distortions that can promote large ferroelectricity in BiFeO3 with an R3c structure [1], but suppress ferroelectricity in CaTiO3 with a Pbnm symmetry [2]. For many CaTiO3-like perovskites, the BiFeO3 structure is a metastable phase. Here, we report the stabilization of the highly-polar BiFeO3-like phase of CaTiO3 in a BaTiO3/CaTiO3 superlattice grown on a SrTiO3 substrate. The stabilization is realized by a reconstruction of oxygen octahedron rotations at the interface from the pattern of nonpolar bulk CaTiO3 to a different pattern that is characteristic of a BiFeO3 phase. The reconstruction is interpreted through a combination of amplitude-contrast sub 0.1nm high-resolution transmission electron microscopy and first-principles theories of the structure, energetics, and polarization of the superlattice and its constituents. We further predict a number of new artificial ferroelectric materials demonstrating that nonpolar perovskites can be turned into ferroelectrics via this interface mechanism. Therefore, a large number of perovskites with the CaTiO3 structure type, which include many magnetic representatives, are now good candidates as novel highly-polar multiferroic materials [3]., Comment: Phys. Rev. X, in production

We performed first principles calculations for epitaxially strained orthorhombic CaTiO$_3$. The computational results reveal the existence of a metastable ferroelectric phase at compressive strain with unexpected in-plane polarization. Symmetry analysis indicates that two distortion modes at the X point combine to induce the polarization, leading to characterization as a hybrid improper ferroelectric. Our work demonstrates a mechanism for improper ferroelectricity in simple perovskites without the need for symmetry lowering by layering or cation ordering.