Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics

Motion forecasting for on-road traffic agents presents both a significant challenge and a critical necessity for ensuring safety in autonomous driving systems. In contrast to most existing data-driven approaches that directly predict future trajectories, we rethink this task from a planning perspective, advocating a "First Reasoning, Then Forecasting" strategy that explicitly incorporates behavior intentions as spatial guidance for trajectory prediction. To achieve this, we introduce an interpretable, reward-driven intention reasoner grounded in a novel query-centric Inverse Reinforcement Learning (IRL) scheme. Our method first encodes traffic agents and scene elements into a unified vectorized representation, then aggregates contextual features through a query-centric paradigm. This enables the derivation of a reward distribution, a compact yet informative representation of the target agent's behavior within the given scene context via IRL. Guided by this reward heuristic, we perform policy rollouts to reason about multiple plausible intentions, providing valuable priors for subsequent trajectory generation. Finally, we develop a hierarchical DETR-like decoder integrated with bidirectional selective state space models to produce accurate future trajectories along with their associated probabilities. Extensive experiments on the large-scale Argoverse and nuScenes motion forecasting datasets demonstrate that our approach significantly enhances trajectory prediction confidence, achieving highly competitive performance relative to state-of-the-art methods.

Dual LiDAR-Based Traffic Movement Count Estimation at a Signalized Intersection: Deployment, Data Collection, and Preliminary Analysis

Traffic Movement Count (TMC) at intersections is crucial for optimizing signal timings, assessing the performance of existing traffic control measures, and proposing efficient lane configurations to minimize delays, reduce congestion, and promote safety. Traditionally, methods such as manual counting, loop detectors, pneumatic road tubes, and camera-based recognition have been used for TMC estimation. Although generally reliable, camera-based TMC estimation is prone to inaccuracies under poor lighting conditions during harsh weather and nighttime. In contrast, Light Detection and Ranging (LiDAR) technology is gaining popularity in recent times due to reduced costs and its expanding use in 3D object detection, tracking, and related applications. This paper presents the authors' endeavor to develop, deploy and evaluate a dual-LiDAR system at an intersection in the city of Rialto, California, for TMC estimation. The 3D bounding box detections from the two LiDARs are used to classify vehicle counts based on traffic directions, vehicle movements, and vehicle classes. This work discusses the estimated TMC results and provides insights into the observed trends and irregularities. Potential improvements are also discussed that could enhance not only TMC estimation, but also trajectory forecasting and intent prediction at intersections.

Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning

Safe and effective motion planning is crucial for autonomous robots. Diffusion models excel at capturing complex agent interactions, a fundamental aspect of decision-making in dynamic environments. Recent studies have successfully applied diffusion models to motion planning, demonstrating their competence in handling complex scenarios and accurately predicting multi-modal future trajectories. Despite their effectiveness, diffusion models have limitations in training objectives, as they approximate data distributions rather than explicitly capturing the underlying decision-making dynamics. However, the crux of motion planning lies in non-differentiable downstream objectives, such as safety (collision avoidance) and effectiveness (goal-reaching), which conventional learning algorithms cannot directly optimize. In this paper, we propose a reinforcement learning-based training scheme for diffusion motion planning models, enabling them to effectively learn non-differentiable objectives that explicitly measure safety and effectiveness. Specifically, we introduce a reward-weighted dynamic thresholding algorithm to shape a dense reward signal, facilitating more effective training and outperforming models trained with differentiable objectives. State-of-the-art performance on pedestrian datasets (CrowdNav, ETH-UCY) compared to various baselines demonstrates the versatility of our approach for safe and effective motion planning.

Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs

Mental visualization, the ability to construct and manipulate visual representations internally, is a core component of human cognition and plays a vital role in tasks involving reasoning, prediction, and abstraction. Despite the rapid progress of Multimodal Large Language Models (MLLMs), current benchmarks primarily assess passive visual perception, offering limited insight into the more active capability of internally constructing visual patterns to support problem solving. Yet mental visualization is a critical cognitive skill in humans, supporting abilities such as spatial navigation, predicting physical trajectories, and solving complex visual problems through imaginative simulation. To bridge this gap, we introduce Hyperphantasia, a synthetic benchmark designed to evaluate the mental visualization abilities of MLLMs through four carefully constructed puzzles. Each task is procedurally generated and presented at three difficulty levels, enabling controlled analysis of model performance across increasing complexity. Our comprehensive evaluation of state-of-the-art models reveals a substantial gap between the performance of humans and MLLMs. Additionally, we explore the potential of reinforcement learning to improve visual simulation capabilities. Our findings suggest that while some models exhibit partial competence in recognizing visual patterns, robust mental visualization remains an open challenge for current MLLMs.

IANN-MPPI: Interaction-Aware Neural Network-Enhanced Model Predictive Path Integral Approach for Autonomous Driving

Motion planning for autonomous vehicles (AVs) in dense traffic is challenging, often leading to overly conservative behavior and unmet planning objectives. This challenge stems from the AVs' limited ability to anticipate and respond to the interactive behavior of surrounding agents. Traditional decoupled prediction and planning pipelines rely on non-interactive predictions that overlook the fact that agents often adapt their behavior in response to the AV's actions. To address this, we propose Interaction-Aware Neural Network-Enhanced Model Predictive Path Integral (IANN-MPPI) control, which enables interactive trajectory planning by predicting how surrounding agents may react to each control sequence sampled by MPPI. To improve performance in structured lane environments, we introduce a spline-based prior for the MPPI sampling distribution, enabling efficient lane-changing behavior. We evaluate IANN-MPPI in a dense traffic merging scenario, demonstrating its ability to perform efficient merging maneuvers. Our project website is available at https://sites.google.com/berkeley.edu/iann-mppi

Predicting Delayed Trajectories Using Network Features: A Study on the Dutch Railway Network

The Dutch railway network is one of the busiest in the world, with delays being a prominent concern for the principal passenger railway operator NS. This research addresses a gap in delay prediction studies within the Dutch railway network by employing an XGBoost Classifier with a focus on topological features. Current research predominantly emphasizes short-term predictions and neglects the broader network-wide patterns essential for mitigating ripple effects. This research implements and improves an existing methodology, originally designed to forecast the evolution of the fast-changing US air network, to predict delays in the Dutch Railways. By integrating Node Centrality Measures and comparing multiple classifiers like RandomForest, DecisionTree, GradientBoosting, AdaBoost, and LogisticRegression, the goal is to predict delayed trajectories. However, the results reveal limited performance, especially in non-simultaneous testing scenarios, suggesting the necessity for more context-specific adaptations. Regardless, this research contributes to the understanding of transportation network evaluation and proposes future directions for developing more robust predictive models for delays.

MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding

Humans are integral components of the transportation ecosystem, and understanding their behaviors is crucial to facilitating the development of safe driving systems. Although recent progress has explored various aspects of human behavior$\unicode{x2014}$such as motion, trajectories, and intention$\unicode{x2014}$a comprehensive benchmark for evaluating human behavior understanding in autonomous driving remains unavailable. In this work, we propose $\textbf{MMHU}$, a large-scale benchmark for human behavior analysis featuring rich annotations, such as human motion and trajectories, text description for human motions, human intention, and critical behavior labels relevant to driving safety. Our dataset encompasses 57k human motion clips and 1.73M frames gathered from diverse sources, including established driving datasets such as Waymo, in-the-wild videos from YouTube, and self-collected data. A human-in-the-loop annotation pipeline is developed to generate rich behavior captions. We provide a thorough dataset analysis and benchmark multiple tasks$\unicode{x2014}$ranging from motion prediction to motion generation and human behavior question answering$\unicode{x2014}$thereby offering a broad evaluation suite. Project page : https://MMHU-Benchmark.github.io.

Guiding LLM Decision-Making with Fairness Reward Models

Large language models are increasingly used to support high-stakes decisions, potentially influencing who is granted bail or receives a loan. Naive chain-of-thought sampling can improve average decision accuracy, but has also been shown to amplify unfair bias. To address this challenge and enable the trustworthy use of reasoning models in high-stakes decision-making, we propose a framework for training a generalizable Fairness Reward Model (FRM). Our model assigns a fairness score to LLM reasoning, enabling the system to down-weight biased trajectories and favor equitable ones when aggregating decisions across reasoning chains. We show that a single Fairness Reward Model, trained on weakly supervised, LLM-annotated examples of biased versus unbiased reasoning, transfers across tasks, domains, and model families without additional fine-tuning. Applied to real-world decision-making tasks including recidivism prediction and social media moderation, we show that our approach consistently improves fairness while matching, or even surpassing, baseline accuracy.

ILNet: Trajectory Prediction with Inverse Learning Attention for Enhancing Intention Capture

Trajectory prediction for multi-agent interaction scenarios is a crucial challenge. Most advanced methods model agent interactions by efficiently factorized attention based on the temporal and agent axes. However, this static and foward modeling lacks explicit interactive spatio-temporal coordination, capturing only obvious and immediate behavioral intentions. Alternatively, the modern trajectory prediction framework refines the successive predictions by a fixed-anchor selection strategy, which is difficult to adapt in different future environments. It is acknowledged that human drivers dynamically adjust initial driving decisions based on further assumptions about the intentions of surrounding vehicles. Motivated by human driving behaviors, this paper proposes ILNet, a multi-agent trajectory prediction method with Inverse Learning (IL) attention and Dynamic Anchor Selection (DAS) module. IL Attention employs an inverse learning paradigm to model interactions at neighboring moments, introducing proposed intentions to dynamically encode the spatio-temporal coordination of interactions, thereby enhancing the model's ability to capture complex interaction patterns. Then, the learnable DAS module is proposed to extract multiple trajectory change keypoints as anchors in parallel with almost no increase in parameters. Experimental results show that the ILNet achieves state-of-the-art performance on the INTERACTION and Argoverse motion forecasting datasets. Particularly, in challenged interaction scenarios, ILNet achieves higher accuracy and more multimodal distributions of trajectories over fewer parameters. Our codes are available at https://github.com/mjZeng11/ILNet.

On the Effect of Uncertainty on Layer-wise Inference Dynamics

Understanding how large language models (LLMs) internally represent and process their predictions is central to detecting uncertainty and preventing hallucinations. While several studies have shown that models encode uncertainty in their hidden states, it is underexplored how this affects the way they process such hidden states. In this work, we demonstrate that the dynamics of output token probabilities across layers for certain and uncertain outputs are largely aligned, revealing that uncertainty does not seem to affect inference dynamics. Specifically, we use the Tuned Lens, a variant of the Logit Lens, to analyze the layer-wise probability trajectories of final prediction tokens across 11 datasets and 5 models. Using incorrect predictions as those with higher epistemic uncertainty, our results show aligned trajectories for certain and uncertain predictions that both observe abrupt increases in confidence at similar layers. We balance this finding by showing evidence that more competent models may learn to process uncertainty differently. Our findings challenge the feasibility of leveraging simplistic methods for detecting uncertainty at inference. More broadly, our work demonstrates how interpretability methods may be used to investigate the way uncertainty affects inference.