X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving

Predicting future states is essential for autonomous agents, yet current Vision-Language-Action (VLA) models fundamentally lack this capability, relying instead on reactive perception-action mapping. While integrating Predictive World Models (PWMs) addresses this gap, existing approaches either incur prohibitive cascaded latency or act as shallow terminal tasks that fail to deeply embed forward-looking reasoning. To endow VLA models with this reasoning capability, we propose X-Mind. Rather than treating PWMs as an external auxiliary module, this framework internalizes them as the Visual Chain-of-Thought (Visual CoT). By enforcing a world rollout prior to action, the model is constrained to imagine future evolution first, yielding a driving policy that is robustly grounded in environmental dynamics and aware of the future consequences its actions will unfold. The challenge here is efficiency, and we tackle it on two fronts. First, we introduce a compact representation of visual thinking: an abstract sketch that fuses a Bird's-Eye-View (BEV) layout with abstract driving priors (e.g., navigation intents and traffic rules). Rather than rolling out dense future frames, the model reasons over this sketch as a mental canvas; aided by a Deep Compression Autoencoder (DC-AE), a 12-frame future rollout is reduced to merely 96 tokens, alleviating the long-context computational bottleneck. Second, to accelerate generation further, we propose a recurrent block diffusion scheme that unrolls the denoising steps across the layers of the large drive model, folding iterative refinement into the backbone's one forward pass. Trained and validated on large-scale real-world data, X-Mind achieves competitive end-to-end driving performance, which makes it a highly practical, low-latency solution that successfully deploys large-scale cognitive reasoning directly onto resource-constrained vehicle platforms.

Optimal Trajectory Generation for Autonomous Vehicles Under Centripetal Acceleration Constraints for In-lane Driving Scenarios

This paper presents a noval method that generates optimal trajectories for autonomous vehicles for in-lane driving scenarios. The method computes a trajectory using a two-phase optimization procedure. In the first phase, the optimization procedure generates a close-form driving guide line with differetiable curvatures. In the second phase, the procedure takes the driving guide line as input, and outputs dynamically feasible, jerk and time optimal trajectories for vehicles driving along the guide line. This method is especially useful for generating trajectories at curvy road where the vehicles need to apply frequent accelerations and decelerations to accommodate centripetal acceleration limits.

Optimal Vehicle Path Planning Using Quadratic Optimization for Baidu Apollo Open Platform

Path planning is a key component in motion planning for autonomous vehicles. A path specifies the geometrical shape that the vehicle will travel, thus, it is critical to safe and comfortable vehicle motions. For urban driving scenarios, autonomous vehicles need the ability to navigate in cluttered environment, e.g., roads partially blocked by a number of vehicles/obstacles on the sides. How to generate a kinematically feasible and smooth path, that can avoid collision in complex environment, makes path planning a challenging problem. In this paper, we present a novel quadratic programming approach that generates optimal paths with resolution-complete collision avoidance capability.

Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization

We present a learning-based planner that aims to robustly drive a vehicle by mimicking human drivers' driving behavior. We leverage a mid-to-mid approach that allows us to manipulate the input to our imitation learning network freely. With that in mind, we propose a novel feedback synthesizer for data augmentation. It allows our agent to gain more driving experience in various previously unseen environments that are likely to encounter, thus improving overall performance. This is in contrast to prior works that rely purely on random synthesizers. Furthermore, rather than completely commit to imitating, we introduce task losses that penalize undesirable behaviors, such as collision, off-road, and so on. Unlike prior works, this is done by introducing a differentiable vehicle rasterizer that directly converts the waypoints output by the network into images. This effectively avoids the usage of heavyweight ConvLSTM networks, therefore, yields a faster model inference time. About the network architecture, we exploit an attention mechanism that allows the network to reason critical objects in the scene and produce better interpretable attention heatmaps. To further enhance the safety and robustness of the network, we add an optional optimization-based post-processing planner improving the driving comfort. We comprehensively validate our method's effectiveness in different scenarios that are specifically created for evaluating self-driving vehicles. Results demonstrate that our learning-based planner achieves high intelligence and can handle complex situations. Detailed ablation and visualization analysis are included to further demonstrate each of our proposed modules' effectiveness in our method.

TDR-OBCA: A Reliable Planner for Autonomous Driving in Free-Space Environment

This paper presents an optimization-based collision avoidance trajectory generation method for autonomous driving in free-space environments, with enhanced robust-ness, driving comfort and efficiency. Starting from the hybrid optimization-based framework, we introduces two warm start methods, temporal and dual variable warm starts, to improve the efficiency. We also reformulates the problem to improve the robustness and efficiency. We name this new algorithm TDR-OBCA. With these changes, compared with original hybrid optimization we achieve a 96.67% failure rate decrease with respect to initial conditions, 13.53% increase in driving comforts and 3.33% to 44.82% increase in planner efficiency as obstacles number scales. We validate our results in hundreds of simulation scenarios and hundreds of hours of public road tests in both U.S. and China. Our source code is availableathttps://github.com/ApolloAuto/apollo.

DL-IAPS and PJSO: A Path/Speed Decoupled Trajectory Optimization and its Application in Autonomous Driving

This paper presents a free space trajectory optimization algorithm of autonomous driving vehicle, which decouples the collision-free trajectory planning problem into a Dual-Loop Iterative Anchoring Path Smoothing (DL-IAPS) and a Piece-wise Jerk Speed Optimization (PJSO). The work leads to remarkable driving performance improvements including more precise collision avoidance, higher control feasibility and better driving comfort, as those are often hard to realize in other existing path/speed decoupled trajectory optimization methods. Our algorithm's efficiency, robustness and adaptiveness to complex driving scenarios have been validated by both simulations and real on-road tests.