INFER: INtermediate representations for FuturE pRediction

Srikanth, Shashank; Ansari, Junaid; Ram, Ranjith; Sharma, Shubham; Murthy, J. Krishna; Krishna, K. Madhava

doi:10.1109/iros40897.2019.8968553

Cited by 40 publications

(54 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For vehicle trajectory prediction, the focus shifts on the observation of motion of individual agents (their past trajectory) and the understanding of the surrounding environment [11], [51], [52]. Traffic dynamics likely reduce to simpler scenarios where movement is limited and constrained by the environment.…”

Section: Related Workmentioning

confidence: 99%

“…Traffic dynamics likely reduce to simpler scenarios where movement is limited and constrained by the environment. Efforts have been made to understand and predict vehicle trajectories in urban scenarios [40], [51], [52], [53], [54], [55], [56], [57], [58], [59], also taking into account social interactions. Although, from the empirical evidence presented in [11], [51], the explicit modeling of social interactions for vehicles was shown not to provide valuable improvements in trajectory prediction.…”

Section: Related Workmentioning

confidence: 99%

“…Distinguished systems that provide multiple trajectory prediction in complex environments are DESIRE [51] and INFER [52]. DESIRE uses a Conditional Variational Autoencoder for estimating a distribution from which future trajectories can be sampled.…”

Section: Related Workmentioning

confidence: 99%

“…Another smaller version of the KITTI dataset for trajectory prediction has been recently proposed by [52] and is publicly available. The authors propose 5 different train/test splits and average results over all runs, so we follow this evaluation protocol.…”

Section: Kitti [73]mentioning

confidence: 99%

See 3 more Smart Citations

Multiple Trajectory Prediction of Moving Agents With Memory Augmented Networks

Marchetti

Becattini

Seidenari

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Pedestrians and drivers are expected to safely navigate complex urban environments along with several non cooperating agents. Autonomous vehicles will soon replicate this capability. Each agent acquires a representation of the world from an egocentric perspective and must make decisions ensuring safety for itself and others. This requires to predict motion patterns of observed agents for a far enough future. In this paper we propose MANTRA, a model that exploits memory augmented networks to effectively predict multiple trajectories of other agents, observed from an egocentric perspective. Our model stores observations in memory and uses trained controllers to write meaningful pattern encodings and read trajectories that are most likely to occur in future. We show that our method is able to natively perform multi-modal trajectory prediction obtaining state-of-the art results on four datasets. Moreover, thanks to the non-parametric nature of the memory module, we show how once trained our system can continuously improve by ingesting novel patterns.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Kitti [73]mentioning

confidence: 99%

See 2 more Smart Citations

Multiple Trajectory Prediction of Moving Agents With Memory Augmented Networks

Marchetti

Becattini

Seidenari

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…The ApolloScape dataset [14] has been recently extended with approximately 80k trajectories for a new trajectory prediction task [18]. Trajectories are obtained combining LIDAR and IMU readings and are represented in a world reference system, which is the most common setting for this task [15,22]. Similarly, other common datasets dedicated only to pedestrian trajectories [20,21] are in a top view reference system.…”

Section: Related Workmentioning

confidence: 99%

Vehicle Trajectories from Unlabeled Data Through Iterative Plane Registration

Becattini

Seidenari

Berlincioni

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

One of the most complex aspects of autonomous driving concerns understanding the surrounding environment. In particular, the interest falls on detecting which agents are populating it and how they are moving. The capacity to predict how these may act in the near future would allow an autonomous vehicle to safely plan its trajectory, minimizing the risks for itself and others. In this work we propose an automatic trajectory annotation method exploiting an Iterative Plane Registration algorithm based on homographies and semantic segmentations. The output of our technique is a set of holistic trajectories (past-present-future) paired with a single image context, useful to train a predictive model.

show abstract

SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction

Liu

Pittaluga

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We propose advances that address two key challenges in future trajectory prediction: (i) multimodality in both training data and predictions and (ii) constant time inference regardless of number of agents. Existing trajectory predictions are fundamentally limited by lack of diversity in training data, which is difficult to acquire with sufficient coverage of possible modes. Our first contribution is an automatic method to simulate diverse trajectories in the top-view. It uses pre-existing datasets and maps as initialization, mines existing trajectories to represent realistic driving behaviors and uses a multi-agent vehicle dynamics simulator to generate diverse new trajectories that cover various modes and are consistent with scene layout constraints. Our second contribution is a novel method that generates diverse predictions while accounting for scene semantics and multi-agent interactions, with constant-time inference independent of the number of agents. We propose a convLSTM with novel state pooling operations and losses to predict scene-consistent states of multiple agents in a single forward pass, along with a CVAE for diversity. We validate our proposed multi-agent trajectory prediction approach by training and testing on the proposed simulated dataset and existing real datasets of traffic scenes. In both cases, our approach outperforms SOTA methods by a large margin, highlighting the benefits of both our diverse dataset simulation and constant-time diverse trajectory prediction methods.

show abstract

INFER: INtermediate representations for FuturE pRediction

Cited by 40 publications

References 15 publications

Multiple Trajectory Prediction of Moving Agents With Memory Augmented Networks

Multiple Trajectory Prediction of Moving Agents With Memory Augmented Networks

Vehicle Trajectories from Unlabeled Data Through Iterative Plane Registration

SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction

Contact Info

Product

Resources

About