Search results

This paper argues for the need to use multiple sources and methods that respond to research challenges presented by new forms of war. There are methodological constraints and contention on the superiority given to positivist and interpretivist research designs when doing fieldwork in war situations, hence there is a need to use integrated data generation techniques. The combined effect of severe limitations of movement for both the researcher and researched fragmented data because of polarized views about the causes of the war and unpredictable events that make information hard to come by militate against systematic, organised and robust data generation. The purpose of this paper, therefore, is to make fieldwork researchers understand significant research problems unique to war zones.

This research was guided by the postmodernist mode of thought which challenges standardised research traditions. Fieldwork experiences in Cabo suggest the need to use the composite strategies that rely on the theoretical foundation of integrative and creative collection of data when doing research in violent settings.

The fieldwork experiences showed that the standardised, conventional and valorised positivist and ethnographic research strategies may not sufficiently facilitate understanding of the dynamics of war. There should not be firm rules, guidelines or regulations governing the actions of the researcher in conflict. As such, doing research in violent settings require reflexivity, flexibility and creativity in research strategies that respond to rapid changes. Research experiences in Mozambique show the need to use blended methods that include even less structured methodologies.

Fieldwork experiences in Cabo challenges researchers who cling to standardised research traditions which often hamper awareness of new postmodernist mode of thought applicable to war settings. It is essential to study the nature of African armed conflicts by combining creativity and flexibility in the selection of research strategies.

Because of the various advantages of reinforcement learning (RL) mentioned above, this study uses RL to train unmanned aerial vehicles to perform two tasks: target search and cooperative obstacle avoidance.

This study draws inspiration from the recurrent state-space model and recurrent models (RPM) to propose a simpler yet highly effective model called the unmanned aerial vehicles prediction model (UAVPM). The main objective is to assist in training the UAV representation model with a recurrent neural network, using the soft actor-critic algorithm.

This study proposes a generalized actor-critic framework consisting of three modules: representation, policy and value. This architecture serves as the foundation for training UAVPM. This study proposes the UAVPM, which is designed to aid in training the recurrent representation using the transition model, reward recovery model and observation recovery model. Unlike traditional approaches reliant solely on reward signals, RPM incorporates temporal information. In addition, it allows the inclusion of extra knowledge or information from virtual training environments. This study designs UAV target search and UAV cooperative obstacle avoidance tasks. The algorithm outperforms baselines in these two environments.

It is important to note that UAVPM does not play a role in the inference phase. This means that the representation model and policy remain independent of UAVPM. Consequently, this study can introduce additional “cheating” information from virtual training environments to guide the UAV representation without concerns about its real-world existence. By leveraging historical information more effectively, this study enhances UAVs’ decision-making abilities, thus improving the performance of both tasks at hand.