Lucian Busoniu

Serban Sabau, Irinel-Constantin Morarescu, Lucian Busoniu et al.

We introduce a distributed control architecture for a class of heterogeneous, nonlinear dynamical agents moving in the "string" formation, while guaranteeing trajectory tracking, collision avoidance and the preservation of the formation's topology. Each autonomous agent uses information and relative measurements only with respect to its predecessor in the string. The performance of the scheme is independent of the number of agents in the network and also on the agent's relative position in the network. The scalability is a consequence of the "decoupling" of a certain bounded approximation of the closed--loop equations, which allows the regulation and controller design (at each agent) to be done individually, in a completely decentralized manner. A practical method for compensating communication induced delays is also presented. Numerical examples illustrate the effectiveness and the main features of the proposed approach.

Bilal Yousuf, Zsofia Lendek, Lucian Busoniu

We address the problem of searching for an unknown number of stationary targets at unknown positions with a mobile agent. A probability hypothesis density filter is used to estimate the expected number of targets under measurement uncertainty. Existing planners, such as Active Search (AS) and its Intermittent variant (ASI), achieve accurate detection but require costly online optimization. To reduce online computation, we propose to use a convolutional neural network to approximate AS or ASI decisions through direct inference. The network is trained on AS/ASI data using a multi-channel grid that encodes target beliefs, the agent position, visitation history, and boundary information. Simulations with uniform and clustered target distributions show that the network achieves detection rates comparable to AS or ASI while reducing computation by orders of magnitude.

Matthias Rosynski, Alexandru Pop, Lucian Busoniu

We consider a problem in which the trajectory of a mobile 3D sensor must be optimized so that certain objects are both found in the overall scene and covered by the point cloud, as fast as possible. This problem is called target search and coverage, and the paper provides an end-to-end deep reinforcement learning (RL) solution to solve it. The deep neural network combines four components: deep hierarchical feature learning occurs in the first stage, followed by multi-head transformers in the second, max-pooling and merging with bypassed information to preserve spatial relationships in the third, and a distributional dueling network in the last stage. To evaluate the method, a simulator is developed where cylinders must be found by a Kinect sensor. A network architecture study shows that deep hierarchical feature learning works for RL and that by using farthest point sampling (FPS) we can reduce the amount of points and achieve not only a reduction of the network size but also better results. We also show that multi-head attention for point-clouds helps to learn the agent faster but converges to the same outcome. Finally, we compare RL using the best network with a greedy baseline that maximizes immediate rewards and requires for that purpose an oracle that predicts the next observation. We decided RL achieves significantly better and more robust results than the greedy strategy.

Eugen Barbulescu, Antonio Alexoaie, Lucian Busoniu

Network pruning is used to reduce inference latency and power consumption in large neural networks. However, most current pruning methods rely on ad-hoc heuristics that are poorly understood. We introduce Hyperflux, a conceptually-grounded pruning method, and use it to study the pruning process. Hyperflux models this process as an interaction between weight flux, the gradient's response to the weight's removal, and network pressure, a global regularization driving weights towards pruning. We postulate properties that arise naturally from our framework and find that the relationship between minimum flux among weights and density follows a power-law equation. Furthermore, we hypothesize the power-law relationship to hold for any effective saliency metric and call this idea the Neural Pruning Law Hypothesis. We validate our hypothesis on several families of pruning methods (magnitude, gradients, $L_0$), providing a potentially unifying property for neural pruning.

Cosmin Ginerica, Mihai Zaha, Florin Gogianu et al.

A key component in autonomous driving is the ability of the self-driving car to understand, track and predict the dynamics of the surrounding environment. Although there is significant work in the area of object detection, tracking and observations prediction, there is no prior work demonstrating that raw observations prediction can be used for motion planning and control. In this paper, we propose ObserveNet Control, which is a vision-dynamics approach to the predictive control problem of autonomous vehicles. Our method is composed of a: i) deep neural network able to confidently predict future sensory data on a time horizon of up to 10s and ii) a temporal planner designed to compute a safe vehicle state trajectory based on the predicted sensory data. Given the vehicle's historical state and sensing data in the form of Lidar point clouds, the method aims to learn the dynamics of the observed driving environment in a self-supervised manner, without the need to manually specify training labels. The experiments are performed both in simulation and real-life, using CARLA and RovisLab's AMTU mobile platform as a 1:4 scaled model of a car. We evaluate the capabilities of ObserveNet Control in aggressive driving contexts, such as overtaking maneuvers or side cut-off situations, while comparing the results with a baseline Dynamic Window Approach (DWA) and two state-of-the-art imitation learning systems, that is, Learning by Cheating (LBC) and World on Rails (WOR).

Florin Gogianu, Tudor Berariu, Mihaela Rosca et al.

Most of the recent deep reinforcement learning advances take an RL-centric perspective and focus on refinements of the training objective. We diverge from this view and show we can recover the performance of these developments not by changing the objective, but by regularising the value-function estimator. Constraining the Lipschitz constant of a single layer using spectral normalisation is sufficient to elevate the performance of a Categorical-DQN agent to that of a more elaborated \rainbow{} agent on the challenging Atari domain. We conduct ablation studies to disentangle the various effects normalisation has on the learning dynamics and show that is sufficient to modulate the parameter updates to recover most of the performance of spectral normalisation. These findings hint towards the need to also focus on the neural component and its learning dynamics to tackle the peculiarities of Deep Reinforcement Learning.