DiPCAN: Distilling Privileged Information for Crowd-Aware Navigation (original) (raw)

DenseCAvoid: Real-time Navigation in Dense Crowds using Anticipatory Behaviors

2020 IEEE International Conference on Robotics and Automation (ICRA), 2020

We present DenseCAvoid, a novel navigation algorithm for navigating a robot through dense crowds and avoiding collisions by anticipating pedestrian behaviors. Our formulation uses visual sensors and a pedestrian trajectory prediction algorithm to track pedestrians in a set of input frames and provide bounding boxes that extrapolate the pedestrian positions in a future time. Our hybrid approach combines this trajectory prediction with a Deep Reinforcement Learning-based collision avoidance method to train a policy to generate smoother, safer, and more robust trajectories during run-time. We train our policy in realistic 3-D simulations of static and dynamic scenarios with multiple pedestrians. In practice, our hybrid approach generalizes well to unseen, real-world scenarios and can navigate a robot through dense crowds (∼1-2 humans per square meter) in indoor scenarios, including narrow corridors and lobbies. As compared to cases where prediction was not used, we observe that our method reduces the occurrence of the robot freezing in a crowd by up to 48%, and performs comparably with respect to trajectory lengths and mean arrival times to goal.

DeepMoTIon: Learning to Navigate Like Humans

2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

We present a novel human-aware navigation approach, where the robot learns to mimic humans to navigate safely in crowds. The presented model, referred to as Deep-MoTIon, is trained with pedestrian surveillance data to predict human velocity in the environment. The robot processes LiDAR scans via the trained network to navigate to the target location. We conduct extensive experiments to assess the components of our network and prove their necessity to imitate humans. Our experiments show that DeepMoTIion outperforms all the benchmarks in terms of human imitation, achieving a 24% reduction in time series-based path deviation over the next best approach. In addition, while many other approaches often failed to reach the target, our method reached the target in 100% of the test cases while complying with social norms and ensuring human safety.

Dynamically Feasible Deep Reinforcement Learning Policy for Robot Navigation in Dense Mobile Crowds

ArXiv, 2020

We present a novel Deep Reinforcement Learning (DRL) based policy for mobile robot navigation in dynamic environments that computes dynamically feasible and spatially aware robot velocities. Our method addresses two primary issues associated with the Dynamic Window Approach (DWA) and DRL-based navigation policies and solves them by using the benefits of one method to fix the issues of the other. The issues are: 1. DWA not utilizing the time evolution of the environment while choosing velocities from the dynamically feasible velocity set leading to sub-optimal dynamic collision avoidance behaviors, and 2. DRL-based navigation policies computing velocities that often violate the dynamics constraints such as the non-holonomic and acceleration constraints of the robot. Our DRL-based method generates velocities that are dynamically feasible while accounting for the motion of the obstacles in the environment. This is done by embedding the changes in the environment's state in a novel ...

Prediction-Based Uncertainty Estimation for Adaptive Crowd Navigation

Artificial Intelligence in HCI, 2020

Fast, collision-free motion through human environments remains a challenging problem for robotic systems. In these situations, the robot's ability to reason about its future motion and other agents is often severely limited. By contrast, biological systems routinely make decisions by taking into consideration what might exist in the future based on prior experience. In this paper, we present an approach that provides robotic systems the ability to make future predictions of the environment. We evaluate several deep network architectures, including purely generative and adversarial models for map prediction. We further extend this approach to predict future pedestrian motion. We show that prediction plays a key role in enabling an adaptive, risk-sensitive control policy. Our algorithms are able to generate future maps with a structural similarity index metric up to 0.899 compared to the ground truth map. Further, our adaptive crowd navigation algorithm is able to reduce the number of collisions by 43% in the presence of novel pedestrian motion not seen during training.

PedLearn : Realtime Pedestrian Tracking , Behavior Learning , and Navigation for Autonomous Vehicles

2017

We present a real-time tracking algorithm for extracting the trajectory of each pedestrian in a crowd video using a combination of non-linear motion models and learning methods. These motion models are based on new collisionavoidance and local navigation algorithms that provide improved accuracy in dense settings. The resulting tracking algorithm can handle dense crowds with tens of pedestrians at realtime rates (25-30fps). We also give an overview of techniques that combine these motion models with global movement patterns and Bayesian inference to predict the future position of each pedestrian over a long time horizon. The combination of local and global features enables us to accurately predict the trajectory of each pedestrian in a dense crowd at realtime rates. We highlight the performance of the algorithm in real-world crowd videos with medium crowd density.

DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles

IEEE Transactions on Robotics

This paper proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate autonomously through spaces filled with both static obstacles and dense crowds of pedestrians. The policy uses a unique combination of input data to generate the desired steering angle and forward velocity: a short history of lidar data, kinematic data about nearby pedestrians, and a sub-goal point. The policy is trained in a reinforcement learning setting using a reward function that contains a novel term based on velocity obstacles to guide the robot to actively avoid pedestrians and move towards the goal. Through a series of 3D simulated experiments with up to 55 pedestrians, this control policy is able to achieve a better balance between collision avoidance and speed (i.e., higher success rate and faster average speed) than state-of-the-art model-based and learningbased policies, and it also generalizes better to different crowd sizes and unseen environments. An extensive series of hardware experiments demonstrate the ability of this policy to directly work in different real-world environments with different crowd sizes with zero retraining. Furthermore, a series of simulated and hardware experiments show that the control policy also works in highly constrained static environments on a different robot platform without any additional training. Lastly, several important lessons that can be applied to other robot learning systems are summarized. Multimedia demonstrations are available at https://www.youtube.com/watch?v=KneELRT8GzU&list= PLouWbAcP4zIvPgaARrV223lf2eiSR-eSS.

Intent-Aware Pedestrian Prediction for Adaptive Crowd Navigation

2020 IEEE International Conference on Robotics and Automation (ICRA), 2020

(JHU) to develop adaptive crowd navigation policies for robots by reasoning and predicting future pedestrian motion. data sets on pedestrians and achieve comparable or better prediction accuracy compared with several stateof-the-art approaches (shown in Table 1). Moreover, we show that confidence in the prediction of pedestrian motion can be used to adjust the risk of a navigation policy adaptively to afford the most comfortable level as measured by the frequency of personal space violation in comparison with baselines. Furthermore, our adaptive navigation policy is able to reduce the number of collisions by 43% in the presence of novel pedestrian motion not seen during training. TECHNICAL APPROACH Machine learning has had a significant impact on many domains, including object recognition, natural language processing, and speech recognition. In recent years, we have seen a significant rise in the use of machine learning, and reinforcement learning specifically, for robotic navigation tasks. The advantage is that robotic systems are now capable of learning skills versus

Towards Safe Navigation Through Crowded Dynamic Environments

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021

This paper proposes a novel neural network-based control policy to enable a mobile robot to navigate safety through environments filled with both static obstacles, such as tables and chairs, and dense crowds of pedestrians. The network architecture uses early fusion to combine a short history of lidar data with kinematic data about nearby pedestrians. This kinematic data is key to enable safe robot navigation in these uncontrolled, human-filled environments. The network is trained in a supervised setting, using expert demonstrations to learn safe navigation behaviors. A series of experiments in detailed simulated environments demonstrate the efficacy of this policy, which is able to achieve a higher success rate than either standard model-based planners or state-of-the-art neural network control policies that use only raw sensor data.

Learning a Group-Aware Policy for Robot Navigation

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Human-aware robot navigation promises a range of applications in which mobile robots bring versatile assistance to people in common human environments. While prior research has mostly focused on modeling pedestrians as independent, intentional individuals, people move in groups; consequently, it is imperative for mobile robots to respect human groups when navigating around people. This paper explores learning group-aware navigation policies based on dynamic group formation using deep reinforcement learning. Through simulation experiments, we show that group-aware policies, compared to baseline policies that neglect human groups, achieve greater robot navigation performance (e.g., fewer collisions), minimize violation of social norms and discomfort, and reduce the robot's movement impact on pedestrians. Our results contribute to the development of social navigation and the integration of mobile robots into human environments.

Deep adaptive learning for safe and efficient navigation of pedestrian dynamics

IET Intelligent Transport Systems, 2021

An efficient and safe evacuation of passengers is important during emergencies. Overcapacity on a route can cause an increased evacuation time. Decision making is essential to optimally guide and distribute pedestrians to multiple routes while ensuring safety. Developing an optimal pedestrian path planning route while considering learning dynamics and uncertainties in the environment generated from pedestrian behaviour is challenging. While previous evacuation planning studies have focused on either simulation of realistic behaviours or simple route planning, the best route decisions with several intermediate decision-points, especially under real-time changing environments, have not been considered. This paper develops an optimal navigation model providing more navigation guidance for evacuation emergencies to minimize the total evacuation time while considering the influence of other passengers based on the social-force model. The integration of the optimal navigation model was ultimately able to reduce the overall evacuation time of multiple scenarios presented with two different overall pedestrian totals. The overall maximum evacuation time savings presented was 10.6%.