The PhD study is aiming to increase the accuracy and efficiency of human-robot collaborative (HRC) assembly systems. To achieve this goal, four main directions are investigated in this research. The first direction is HRC assembly context recognition, which focuses on the identification and recognition of relevant assembly context in the assembly environment. Valuable knowledge can be captured through the assembly context to increase assembly efficiency. The definition of assembly context is given, and recognition algorithms are designed. The second direction is multimodal robot control. Instead of coding, the possibility to control robots with multiple modalities is explored. The algorithm to increase the recognition accuracy of multimodal robot control is developed. The third direction is human motion prediction. Robots can be supported to anticipate and prepare for the human operator' next move with an accurate and timely prediction of the human operator's motion. Two different approaches are explored to predict human motions during the assembly operation. The efficiency of HRC assembly systems can be further boosted. The last direction of the study is remote HRC. A special scenario of HRC is explored where a human operator collaborates with a robot remotely. The scenario is investigated, a possible solution is also provided. Along with the four directions, key algorithms, system designs, and experiments are analysed. Furthermore, the advantages, drawbacks, and future directions of the approaches are given. ; Doktorand Studien syfte är att öka noggrannheten och effektiviteten i human-robot collaborative (HRC) monteringssystem. För att uppnå detta mål, fyra huvudinriktningar undersöks i denna forskning. Den första riktningen är HRC monterings kontext igenkänning, som fokuserar på identifiering och igenkänning av relevant monterings kontext i monterings miljö. Värdefull information kan fångas genom monterings-kontext för att öka monterings-effektiviteten. Definition av monterings kontext anges och ...