Vision-Guided MPC for Robotic Path Following Using Learned Memory-Augmented Model

The control of the interaction between the robot and environment, following a predefined geometric surface path with high accuracy, is a fundamental problem for contact-rich tasks such as machining, polishing, or grinding. Flexible path-following control presents numerous applications in emerging industry fields such as disassembly and recycling, where the control system must adapt to a range of dissimilar object classes, where the properties of the environment are uncertain. We present an end-to-end framework for trajectory-independent robotic path following for contact-rich tasks in the presence of parametric uncertainties. We formulate a combination of model predictive control with image-based path planning and real-time visual feedback, based on a learned state-space dynamic model. For modeling the dynamics of the robot-environment system during contact, we introduce the application of the differentiable neural computer, a type of memory augmented neural network (MANN). Although MANNs have been as yet unexplored in a control context, we demonstrate a reduction in RMS error of ∼21.0% compared with an equivalent Long Short-Term Memory (LSTM) architecture. Our framework was validated in simulation, demonstrating the ability to generalize to materials previously unseen in the training dataset.

The role of ‘Rich Tasks’ an interdisciplinary and digital approach to learning post COVID-19

The Covid-19 pandemic has thrown into stark relief the importance of students being able to be flexible learners: juggling blended learning opportunities, being independent and creative, and collaborating with staff and students- often in digital virtual environments. This paper reviews alternative interdisciplinary curriculum models that break down artificial barriers between subject disciplines through the use of ‘Rich Tasks’, interdisciplinary tasks which integrate subject knowledge with developing student skills in the 4C’s collaboration, critical thinking, communication, and creativity. The paper suggests that ‘Rich Tasks’ provide a futureproof methodology as they focus learning on the global, emotionally resilient skills that children need to adapt to a changing digital world where they may change jobs many times. Historic and current interdisciplinary learning models are explored. Interviews with key practitioners and learners who were and are involved in these were conducted. Significantly positive responses to interdisciplinary learning from both groups of respondents are found. A development of the form of learning called ‘Rich Tasks’ (See Moulds 2004 for definitions) can be constructed through the enhanced knowledge and utilisation of digital technology which teachers have gained worldwide in order to continue teaching during the pandemic.

EXPLORING THE USEFULNESS OF RICH MATHEMATICAL TASKS TO ENHANCE STUDENTS’ REFLECTIVE THINKING

Promoting reflective thinking in daily teaching practice is vital to prepare students to live in a more challenging world. Rich tasks are one of the promising tasks that could be used as pedagogy trend to develop students' reflective thinking. Therefore, the purpose of this study is to describe the usefulness of rich mathematical tasks including how teachers use them in their teaching practice and the improvement of students’ reflective thinking following the rich tasks based instruction. This study employed a teaching experiment within a case study design. Participants were 28 Year 7 students of one the junior high school in Aceh, Indonesia. The instrument of the study is three valid and reliable rich mathematical tasks administered to the students through student worksheet. The results of the study show that rich tasks provided students with the opportunity to solve real-world problems by questioning their understanding and thinking reflectively. It also found that most students in the classroom were able to achieve the low level of reflective thinking with classroom mean score is 60. This value fairly enough since reflective thinking is a complicated concept. Subsequently, the results indicate the rich mathematical tasks approach hold potential in enhancing students’ reflective thinking ability.

Hook Line Sinker

The Hook-Line-Sinker eBook aims to utilise rich tasks as the core learning in mathematics rather than a selection of “one-hit-wonders”. The featured resources intend to provide teachers with a starting point for sparking student curiosity, developing the need to learn, and consolidating learning in multiple ways.