Effective interaction modeling and behavior prediction of dynamic agents play a significant role in interactive motion planning for autonomous robots. Although existing methods
have improved prediction accuracy, few research efforts have been devoted to enhancing prediction model interpretability and out-of-distribution (OOD) generalizability. This work addresses these two challenging aspects by designing a variational autoencoder framework that integrates graph-based representations and time-sequence models to efficiently capture spatio-temporal relations between interactive agents and predict their dynamics. Our model infers dynamic interaction graphs in a latent space augmented with interpretable edge features that characterize the interactions. Moreover, we aim to enhance model interpretability and performance in OOD scenarios by disentangling the latent space of edge features, thereby strengthening model versatility and robustness. We validate our approach through extensive experiments on both simulated and real-world datasets. The results show superior performance compared to existing methods in modeling spatio-temporal relations, motion prediction, and identifying time-invariant latent features.

We introduce a novel representation called Ordered Atomic Activity for interactive scenario understanding. The representation decomposes each scenario into a set of ordered atomic activities, where each activity consists of an action and the corresponding actors involved and the order denotes the temporal development of the scenario. The design also helps in identifying important interactive relationships such as yielding. The action is a high-level semantic motion pattern that is grounded in the surrounding road topology, which we decompose into zones and corners with unique IDs. For example, a group of pedestrians crossing on the left side is denoted as C1 → C4: P+, as depicted in Figure 1. We collect a new large-scale dataset called OATS (Ordered Atomic Activities in interactive Traffic Scenarios), comprising 1026 video clips (∼ 20s) captured at intersections. Each clip is labeled with the proposed language, resulting in 59 activity categories and 6512 annotated activity instances. We propose three fine-grained scenario understanding tasks, i.e., multi-label Atomic Activity recognition, recognition, activity order prediction, and interactive scenario retrieval. We implement various state-of-the-art algorithms and conduct extensive experiments on OATS. We found the existing methods cannot achieve satisfactory performance, indicating new opportunities for the community to develop new algorithms for these tasks toward better interactive scenario understanding

We present a novel method for weakly-supervised action segmentation and unseen error detection in anomalous instructional videos. In the absence of an appropriate dataset for this task, we introduce and plan to publicly release the Anomalous Toy Assembly (ATA) dataset, which comprises 1152 untrimmed videos of 32 participants assembling three different toys, recorded from four different viewpoints. The training set comprises 27 participants who assemble toys in an expected and consistent manner, while the test and validation sets comprise 5 participants who display sequential anomalies in their task. We introduce a weakly labeled segmentation algorithm that is a generalization of the constrained Viterbi algorithm and identifies potential anomalous moments based on the difference between future anticipation and current recognition results. The proposed method is not restricted by the training transcripts during testing, allowing for the inference of anomalous action sequences while maintaining real-time performance. Based on these segmentation results, we also introduce a baseline to detect pre-defined human errors, and benchmark results on the ATA dataset. Experiments were conducted on the ATA and CSV datasets, demonstrating that the proposed method outperforms the state-of-the-art in segmenting anomalous videos under both online and offline conditions.

We present RAFTformer, a real-time action forecasting transformer for latency-aware real-world action forecasting. RAFTformer is a two-stage fully transformer based architecture comprising of a video transformer backbone that operates on high resolution, short-range clips, and a head transformer encoder that temporally aggregates information from multiple short-range clips to span a long-term horizon. Additionally, we propose a novel self-supervised shuffled causal masking scheme as a model level augmentation to improve forecasting fidelity. Finally, we also propose a novel real-time evaluation setting for action forecasting that directly couples model inference latency to overall forecasting performance and brings forth a hitherto overlooked trade-off between latency and action forecasting performance. Our parsimonious network design facilitates RAFTformer inference latency to be 9× smaller than prior works at the same forecasting accuracy. Owing to its two-staged design, RAFTformer uses 94% less training compute and 90% lesser training parameters to outperform prior state-of-the-art baselines by 4.9 points on EGTEA Gaze+ and by 1.4 points on EPIC-Kitchens-100 validation set, as measured by Top-5 recall (T5R) in the offline setting. In the real-time setting, RAFTformer outperforms prior works by an even greater margin of upto 4.4 T5R points on the EPIC-Kitchens-100 dataset.

Trajectory prediction is an essential task towards understanding object movement and human behavior from observed sequences. Current methods usually assume that the observed sequences are complete while ignoring the potential for missing values in the observations due to object occlusion, scope limitation, sensor failure, etc., hindering the trajectory prediction accuracy. In our paper, a unified framework, Graph-based Conditional Variational Recurrent Neural Network (GC-VRNN), is proposed to jointly conduct trajectory imputation and prediction. Specifically, a novel Multi-Space Graph Neural Network (MS-GNN) is developed to extract spatial features from incomplete observations, leveraging missing patterns. Additionally, we adopt a Conditional VRNN with a specifically designed Temporal Decay (TD) module to model temporal dependencies and temporal missing patterns of incomplete trajectories. Notably, valuable information is shared via temporal flow. We curate and benchmark three practical datasets for the joint problem of trajectory imputation and prediction. Extensive experiments verify the superior performance of our model. To the best of our knowledge, our work is the pioneer which fills the gap in benchmarks and techniques for trajectory imputation and prediction in a unified way.

Effective understanding of dynamically evolving multiagent interactions is crucial to capturing the underlying behavior of agents in social systems. It is usually challenging to observe these interactions directly, and therefore modeling the latent interactions is essential for realizing the complex behaviors. Recent work on Dynamic Neural Relational Inference (DNRI) captures explicit inter-agent interactions at every step. However, prediction at every step results in noisy interactions and lacks intrinsic interpretability without post-hoc inspection. Moreover, it requires access to ground truth annotations to analyze the predicted interactions, which are hard to obtain. This paper introduces DIDER, Discovering Interpretable Dynamically Evolving Relations, a generic end-to-end interaction modeling framework with intrinsic interpretability. DIDER discovers an interpretable sequence of inter-agent interactions by disentangling the task of latent interaction prediction into sub-interaction prediction and duration estimation. By imposing the consistency of a sub-interaction type over an extended time duration, the proposed framework achieves intrinsic interpretability without requiring any post-hoc inspection. We evaluate DIDER on both synthetic and real-world datasets. The experimental results demonstrate that modeling disentangled and interpretable dynamic relations improves performance on trajectory forecasting tasks.

Considering the functionality of situational awareness in safety-critical automation systems, the perception of risk in driving scenes and its explainability is of particular importance for autonomous and cooperative driving. Toward this goal, this paper proposes a new research direction of joint risk localization in driving scenes and its risk explanation as a natural language description. Due to the lack of standard benchmarks, we collected a large-scale dataset, DRAMA (Driving Risk Assessment Mechanism with A captioning module), which consists of 17,785 interactive driving scenarios collected in Tokyo, Japan. Our DRAMA dataset accommodates video- and object-level questions on driving risks with associated important objects to achieve the goal of visual captioning as a free-form language description utilizing closed and open-ended responses for multi-level questions, which can be used to evaluate a range of visual captioning capabilities in driving scenarios. We make this data available to the community for further research. Using DRAMA, we explore multiple facets of joint risk localization and captioning in interactive driving scenarios. In particular, we benchmark various multi-task prediction architectures and provide a detailed analysis of joint risk localization and risk captioning. The data set will be available

Effective understanding of dynamically evolving multiagent interactions is crucial to capturing the underlying behavior of agents in social systems. It is usually challenging to observe these interactions directly, and therefore modeling the latent interactions is essential for realizing the complex behaviors. Recent work on Dynamic Neural Relational Inference (DNRI) captures explicit inter-agent interactions at every step. However, prediction at every step results in noisy interactions and lacks intrinsic interpretability without post-hoc inspection. Moreover, it requires access to ground truth annotations to analyze the predicted interactions, which are hard to obtain. This letter introduces DIDER, Discovering Interpretable Dynamically Evolving Relations, a generic end-to-end interaction modeling framework with intrinsic interpretability. DIDER discovers an interpretable sequence of inter-agent interactions by disentangling the task of latent interaction prediction into sub-interaction prediction and duration estimation. By imposing the consistency of a sub-interaction type over an extended time duration, the proposed framework achieves intrinsic interpretability without requiring any post-hoc inspection. We evaluate DIDER on both synthetic and real-world datasets. The experimental results demonstrate that modeling disentangled and interpretable dynamic relations improves performance on trajectory forecasting tasks.

Predicting the future trajectory of agents from visual observations is an important problem for realization of safe and effective navigation of autonomous systems in dynamic environments. This paper focuses on two important aspects of future trajectory forecast which are particularly relevant for mobile platforms: 1) modeling uncertainty of the predictions, particularly from egocentric views, where uncertainty in the interactive reactions and behaviors of other agents must consider the uncertainty in the ego-motion, and 2) modeling
multi-modality nature of the problem, which are particularly prevalent at junctions in urban traffic scenes. To address these problems in a unified approach, we propose NEMO (Noisy Ego MOtion priors for future object localization) for future forecast of agents in the egocentric view. In the proposed approach, a predictive distribution of future forecast is jointly modeled with the uncertainty of predictions. For this, we divide the problem into two tasks: future ego-motion prediction and future object localization. We first model the multi-modal distribution of future ego-motion with uncertainty estimates. The resulting distribution of ego-behavior is used to sample multiple modes of future ego-motion. Then, each modality is used as a prior to understand the interactions between the ego-vehicle and target agent. We predict the multi-modal future locations of the target from individual modes of the ego-vehicle while modeling the uncertainty of the target’s behavior. To this end, we extensively evaluate the proposed framework using the publicly available benchmark dataset (HEV-I) supplemented with odometry data from an Inertial Measurement Unit (IMU).

Obtaining accurate and diverse human motion prediction is essential to many industrial applications, especially robotics and autonomous driving. Recent research has explored several techniques to enhance diversity and maintain the accuracy of human motion prediction at the same time. However, most of them need to define a combined loss, such as the weighted sum of accuracy loss and diversity loss, and then decide their weights as hyperparameters before training. In this work, we aim to design a prediction framework that can balance the accuracy sampling and diversity sampling during the testing phase. In order to achieve this target, we propose a multi-objective conditional variational inference prediction model. We also propose a short-term oracle to encourage the prediction framework to explore more diverse future motions. We evaluate the performance of our proposed approach on two standard human motion datasets. The experiment results show that our approach is effective and on a par with state-of-the-art performance in terms of accuracy and diversity.

Accurate identification of important objects in the scene is a prerequisite for safe and high-quality decision making and motion planning of intelligent agents (e.g., autonomous vehicles) that navigate in complex and dynamic environments. Most existing approaches attempt to employ attention mechanisms to learn importance weights associated with each object indirectly via various tasks (e.g., trajectory prediction), which do not enforce direct supervision on the importance estimation. In contrast, we tackle this task in an explicit way and formulate it as a binary classification ("important" or "unimportant") problem. We propose a novel approach for important object identification in egocentric driving scenarios with relational reasoning on the objects in the scene. Besides, since human annotations are limited and expensive to obtain, we present a semi-supervised learning pipeline to enable the model to learn from unlimited unlabeled data. Moreover, we propose to leverage the auxiliary tasks of ego vehicle behavior prediction to further improve the accuracy of importance estimation. The proposed approach is evaluated on a public egocentric driving dataset (H3D) collected in complex traffic scenarios. A detailed ablative study is conducted to demonstrate the effectiveness of each model component and the training strategy. Our approach also outperforms rule-based baselines by a large margin.

Predicting future trajectories of traffic agents in highly interactive environments is an essential and challenging problem for the safe operation of autonomous driving systems. On the basis of the fact that self-driving vehicles are equipped with various types of sensors (e.g., LiDAR scanner, RGB camera, radar, etc.), we propose a Cross-Modal Embedding framework that aims to benefit from the use of multiple input modalities. At training time, our model learns to embed a set of complementary features in a shared latent space by jointly optimizing the objective functions across different types of input data. At test time, a single input modality (e.g., LiDAR data) is required to generate predictions from the input perspective (i.e., in the LiDAR space), while taking advantages from the model trained with multiple sensor modalities. An extensive evaluation is conducted to show the efficacy of the proposed framework using two benchmark driving datasets.

This paper considers the problem of multi-modal future trajectory forecast with ranking. Here, multi-modality and ranking refer to the multiple plausible path predictions and the confidence in those predictions, respectively. We propose Social-STAGE, Social interaction-aware SpatioTemporal multi-Attention Graph convolution network with novel Evaluation for multi-modality. Our main contributions include analysis and formulation of multi-modality with ranking using interaction and multi-attention, and introduction of new metrics to evaluate the diversity and associated confidence of multi-modal predictions. We evaluate our approach on existing public datasets ETH and UCY and show that the proposed algorithm outperforms the state of the arts on these datasets

Multi-agent interacting systems are prevalent in the world, from pure physical systems to complicated social dynamic systems. In many applications, effective understanding of the situation and accurate trajectory prediction of interactive agents play a significant role in downstream tasks, such as decision making and planning. In this paper, we propose a generic trajectory forecasting framework (named EvolveGraph) with explicit relational structure recognition and prediction via latent interaction graphs among multiple heterogeneous, interactive agents. Considering the uncertainty of future behaviors, the model is designed to provide multi-modal prediction hypotheses. Since the underlying interactions may evolve even with abrupt changes, and different modalities of evolution may lead to different outcomes, we address the necessity of dynamic relational reasoning and adaptively evolving the interaction graphs. We also introduce a double-stage training pipeline which not only improves training efficiency and accelerates convergence, but also enhances model performance. The proposed framework is evaluated on both synthetic physics simulations and multiple real-world benchmark datasets in various areas. The experimental results illustrate that our approach achieves state-of-the-art performance in terms of prediction accuracy.

We propose a Deep RObust Goal-Oriented trajectory prediction Network (DROGON) for accurate vehicle trajectory prediction by considering behavioral intentions of vehicles in traffic scenes. Our main insight is that the behavior (i.e., motion) of drivers can be reasoned from their high level possible goals (i.e., intention) on the road. To succeed in such behavior reasoning, we build a conditional prediction model to forecast goal-oriented trajectories with the following stages: (i) relational inference where we encode relational interactions of vehicles using the perceptual context; (ii) intention estimation to compute the probability distributions of intentional goals based on the inferred relations; and (iii) behavior reasoning where we reason about the behaviors of vehicles as trajectories conditioned on the intentions. To this end, we extend the proposed framework to the pedestrian trajectory prediction task, showing the potential applicability toward general trajectory prediction.

We propose a robust solution to future trajectory forecast, which can be practically applicable to autonomous agents in highly crowded environments. For this, three aspects are particularly addressed in this paper. First, we use composite fields to predict future locations of all road agents in a single-shot, which results in a constant time complexity, regardless of the number of agents in the scene. Second, interactions between agents are modeled as a non-local response, enabling spatial relationships between different locations to be captured temporally as well (i.e., in spatio-temporal interactions). Third, the semantic context of the scene are modeled and take into account the environmental constraints that potentially influence the future motion. To this end, we validate the robustness of the proposed approach using the ETH, UCY, and SDD datasets and highlight its practical functionality compared to the current state-of-the-art methods. (Test text added)

Test Content

We consider the problem of predicting the future trajectory of scene agents from egocentric views obtained from a moving platform. This problem is important in a variety of domains, particularly for autonomous systems making reactive or strategic decisions in navigation. In an attempt to address this problem, we introduce TITAN (Trajectory Inference using Targeted Action priors Network), a new model that incorporates prior positions, actions, and context to forecast future trajectory of agents and future ego-motion. In the absence of an appropriate dataset for this task, we created the TITAN dataset that consists of 700 labeled video-clips (with odometry) captured from a moving vehicle on highly interactive urban traffic scenes in Tokyo. Our dataset includes 50 labels including vehicle states and actions, pedestrian age groups, and targeted pedestrian action attributes that are organized hierarchically corresponding to atomic, simple/complex-contextual, transportive, and communicative actions. To evaluate our model, we conducted extensive experiments on the TITAN dataset, revealing significant performance improvement against baselines and state-of-the-art algorithms. We also report promising results from our Agent Importance Mechanism (AIM), a module which provides insight into assessment of perceived risk by calculating the relative influence of each agent on the future ego-trajectory. The dataset is available at https://usa.honda-ri.com/titan

Inferring relational behavior between road users as well as road users and their surrounding physical space is an important step toward effective modeling and prediction of navigation strategies adopted by participants in road scenes. To this end, we propose a relation-aware framework for future trajectory forecast. Our system aims to infer relational information from the interactions of road users with each other and with the environment. The first module involves visual encoding of Spatio-temporal features, which captures human-human and human-space interactions over time. The following module explicitly constructs pair-wise relations from Spatio-temporal interactions and identifies more descriptive relations that highly influence future motion of the target road user by considering its past trajectory. The resulting relational features are used to forecast future locations of the target, in the form of heatmaps with an additional guidance of spatial dependencies and consideration of the uncertainty. Extensive evaluations on the public benchmark datasets demonstrate the robustness and efficacy of the proposed framework as observed by performances higher than the state-of-the-art methods.

Predicting the future location of vehicles is essential for safety-critical applications such as advanced driver assistance systems (ADAS) and autonomous driving. This paper introduces a novel approach to simultaneously predict both the location and scale of target vehicles in the first-person (egocentric) view of an ego-vehicle. We present a multi-stream recurrent neural network (RNN) encoder-decoder model that separately captures both object location and scale and pixel-level observations for future vehicle localization. We show that incorporating dense optical flow improves prediction results significantly since it captures information about motion as well as appearance change. We also find that explicitly modeling future motion of the ego-vehicle improves the prediction accuracy, which could be especially beneficial in intelligent and automated vehicles that have motion planning capability. To evaluate the performance of our approach, we present a new dataset of first-person videos collected from a variety of scenarios at road intersections, which are particularly challenging moments for prediction because vehicle trajectories are diverse and dynamic.

Predicting future action locations is vital for applications like human-robot collaboration. While some computer vision tasks have made progress in predicting human actions, accurately localizing these actions in future frames remains an area with room for improvement. We introduce a new task called spatial action localization in the future (SALF), which aims to predict action locations in both observed and future frames. SALF is challenging because it requires understanding the underlying physics of video observations to predict future action locations accurately. To address SALF, we use the concept of NeuralODE, which models the latent dynamics of sequential data by solving ordinary differential equations (ODE) with neural networks. We propose a novel architecture, AdamsFormer, which extends observed frame features to future time horizons by modeling continuous temporal dynamics through ODE solving. Specifically, we employ the Adams method, a multi-step approach that efficiently uses information from previous steps without discarding it. Our extensive experiments on UCF101-24 and JHMDB-21 datasets demonstrate that our proposed model outperforms existing long-range temporal modeling methods by a significant margin in terms of frame-mAP.

Advanced Driver Assistance Systems (ADAS) with proactive alerts have been used to increase driving safety. Such systems’ performance greatly depends on how accurately and quickly the risky situations and maneuvers are detected. Existing ADAS provide warnings based on the vehicle’s operational status, detection of environments, and the drivers’ overt actions (e.g., using turn signals or steering wheels), which may not give drivers as much as optimal time to react. In this paper, we proposed a spatio-temporal attention-based neural network to predict drivers’ lane-change intention by fusing the videos from both in-cabin and forward perspectives. The Convolutional Neural Network (CNN)-Recursive Neural Network (RNN) network architecture was leveraged to extract both the spatial and temporal information. On top of this network backbone structure, the feature maps from different time steps and perspectives were fused using multi-head self-attention at each resolution of the CNN. The proposed model was trained and evaluated using a processed subset of the MIT Advanced Vehicle Technology (MIT-AVT) dataset which contains synchronized CAN data, 11058-second videos from 3 different views, 548 lane-change events, and 274 non-lane-change events performed by 83 drivers. The results demonstrate that the model achieves 87% F1-score within the 1-second validation window and 70% F1-score within the 5-second validation window with real-time performance.