Multi-Robot Local Motion Planning Using Dynamic Optimization Fabrics

In this paper, we address the problem of real-time motion planning for multiple robotic manipulators that operate in close proximity. We build upon the concept of dynamic fabrics and extend them to multi-robot systems, referred to as Multi-Robot Dynamic Fabrics (MRDF). This geometric method enables a very high planning frequency for high...

Distributed multi-target tracking and active perception with mobile camera networks

Smart cameras are an essential component in surveillance and monitoring applications, and they have been typically deployed in networks of fixed camera locations. The addition of mobile cameras, mounted on robots, can overcome some of the limitations of static networks such as blind spots or back-lightning, allowing the system to gather the...

Active Classification of Moving Targets With Learned Control Policies

In this paper, we consider the problem where a drone has to collect semantic information to classify multiple moving targets. In particular, we address the challenge of computing control inputs that move the drone to informative viewpoints, position and orientation, when the information is extracted using a “black-box” classifier, e.g., a deep...

Learning scalable and efficient communication policies for multi-robot collision avoidance

Decentralized multi-robot systems typically perform coordinated motion planning by constantly broadcasting their intentions to avoid collisions. However, the risk of collision between robots varies as they move and communication may not always be needed. This paper presents an efficient communication method that addresses the problem of “when...

Surrogate DC Microgrid Models for Optimization of Charging Electric Vehicles under Partial Observability

Many electric vehicles (EVs) are using today’s distribution grids, and their flexibility can be highly beneficial for the grid operators. This flexibility can be best exploited by DC power networks, as they allow charging and discharging without extra power electronics and transformation losses. From the grid control perspective, algorithms for...

Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning

Real world multi-agent tasks often involve varying types and quantities of agents and non-agent entities; however, agents within these tasks rarely need to consider all others at all times in order to act effectively. Factored value function approaches have historically leveraged such independences to improve learning efficiency, but these...

UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning

VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a centralized action value function as a monotonic mixing of per-agent utilities. While this enables easy decentralization of the learned policy, the restricted joint action value function can prevent them from solving tasks that require significant coordination...

Transient non-stationarity and generalisation in deep reinforcement learning

Non-stationarity can arise in Reinforcement Learning (RL) even in stationary environments. For example, most RL algorithms collect new data throughout training, using a non-stationary behaviour policy. Due to the transience of this non-stationarity, it is often not explicitly addressed in deep RL and a single neural network is continually...

Reinforcement Learning for the Knapsack Problem

Combinatorial optimization (CO) problems are at the heart of both practical and theoretical research. Due to their complexity, many problems cannot be solved via exact methods in reasonable time; hence, we resort to heuristic solution methods. In recent years, machine learning (ML) has brought immense benefits in many research areas,...

My body is a cage: the role of morphology in graph-based incompatible control

Multitask Reinforcement Learning is a promising way to obtain models with better performance, generalisation, data efficiency, and robustness. Most existing work is limited to compatible settings, where the state and action space dimensions are the same across tasks. Graph Neural Networks (GNN) are one way to address incompatible environments,...

Multitask Soft Option Learning

We present Multitask Soft Option Learning (MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational posteriors for each task, regularized by a shared prior. This “soft” version of options avoids several instabilities during training in a multitask setting, and...

A Compton camera prototype for prompt gamma medical imaging

Compton camera prototype for a position-sensitive detection of prompt γ rays from proton-induced nuclear reactions is being developed in Garching. The detector system allows to track the Comptonscattered electrons. The camera consists of a monolithic LaBr₃:Ce scintillation absorber crystal, read out by a multi-anode PMT, preceded...