Instance-Aware Predictive Navigation in Multi-Agent Environments

@article{Cao2021InstanceAwarePN,
  title={Instance-Aware Predictive Navigation in Multi-Agent Environments},
  author={Jinkun Cao and Xin Wang and Trevor Darrell and Fisher Yu},
  journal={2021 IEEE International Conference on Robotics and Automation (ICRA)},
  year={2021},
  pages={5096-5102}
}
  • Jinkun CaoXin Wang F. Yu
  • Published 14 January 2021
  • Computer Science
  • 2021 IEEE International Conference on Robotics and Automation (ICRA)
In this work, we aim to achieve efficient end-to-end learning of driving policies in dynamic multi-agent environments. Predicting and anticipating future events at the object level are critical for making informed driving decisions. We propose an Instance-Aware Predictive Control (IPC) approach, which forecasts interactions between agents as well as future scene structures. We adopt a novel multi-instance event prediction module to estimate the possible interaction among agents in the ego… 
View on IEEE
arxiv.org
3 Citations

Figures and Tables from this paper

3 Citations

Learning Credit Assignment for Cooperative Reinforcement Learning

MAPPG takes a simple butcient polarization function to transform the optimal consis-tency of joint and individual actions into easily re-alized constraints, thus enabling efficient credit assignment in MAPG, and it is proved that individual policies of MAPPG can converge to the global optimum.

DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion

  • Pei SunJinkun Cao P. Luo
  • Computer Science
    2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2022
A large-scale dataset for multi-human tracking, where humans have sim-ilar appearance, diverse motion and extreme articulation, and is named “DanceTrack”, which is expected to provide a better platform to develop more MOT algorithms that rely less on visual discrimination and depend more on motion analysis.

Deep Learning based Object Detection Model for Autonomous Driving Research using CARLA Simulator

This paper proposes the application of object detection algorithm on CARLA simulator to derive useful results for autonomous driving research and the comparison ofCARLA simulator with other available simulators, key players in the field of autonomous vehicle technology, state-of-the-art algorithms being used for autonomousdriving, real time implementation challenges and future technologies are discussed.

References

SHOWING 1-10 OF 36 REFERENCES

PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings

A probabilistic forecasting model of future interactions between a variable number of agents that performs both standard forecasting and the novel task of conditional forecasting, which reasons about how all agents will likely respond to the goal of a controlled agent.

CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving

This work presents a general and principled Controllable Imitative Reinforcement Learning (CIRL) approach which successfully makes the driving agent achieve higher success rates based on only vision inputs in a high-fidelity car simulator, which performs better than supervised imitation learning.

Semantic Predictive Control for Explainable and Efficient Policy Learning

A driving policy learning framework that predicts feature representations of future visual inputs and a predictive model that infers not only future events but also semantics, which provide a visual explanation of policy decisions are proposed.

End-to-End Driving Via Conditional Imitation Learning

This work evaluates different architectures for conditional imitation learning in vision-based driving and conducts experiments in realistic three-dimensional simulations of urban driving and on a 1/5 scale robotic truck that is trained to drive in a residential area.

Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation

This work proposes a zero-shot imitation learning framework for training a goal-driven visual navigation policy on a legged robot from human demonstrations (third-person perspective), allowing for high-quality navigation and cost-effective data collection.

Deep Object-Centric Policies for Autonomous Driving

A taxonomy of “object-centric” models which leverage both object instances and end-to-end learning are described, showing that object-centric models outperform object-agnostic methods in scenes with other vehicles and pedestrians, even with an imperfect detector.

Social LSTM: Human Trajectory Prediction in Crowded Spaces

This work proposes an LSTM model which can learn general human movement and predict their future trajectories and outperforms state-of-the-art methods on some of these datasets.

Continuous control with deep reinforcement learning

This work presents an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces, and demonstrates that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs.

Virtual to Real Reinforcement Learning for Autonomous Driving

A novel realistic translation network is proposed to make model trained in virtual environment be workable in real world, and is believed to be the first successful case of driving policy trained by reinforcement learning that can adapt to real world driving data.

End to End Learning for Self-Driving Cars

A convolutional neural network is trained to map raw pixels from a single front-facing camera directly to steering commands and it is argued that this will eventually lead to better performance and smaller systems.