Noisy observations coupled with nonlinear dynamics pose one of the biggest challenges in robot mo... more Noisy observations coupled with nonlinear dynamics pose one of the biggest challenges in robot motion planning. By decomposing nonlinear dynamics into a discrete set of local dynamics models, hybrid dynamics provide a natural way to model nonlinear dynamics, especially in systems with sudden discontinuities in dynamics due to factors such as contacts. We propose a hierarchical POMDP planner that develops cost-optimized motion plans for hybrid dynamics models. The hierarchical planner first develops a high-level motion plan to sequence the local dynamics models to be visited and then converts it into a detailed continuous state plan. This hierarchical planning approach results in a decomposition of the POMDP planning problem into smaller sub-parts that can be solved with significantly lower computational costs. The ability to sequence the visitation of local dynamics models also provides a powerful way to leverage the hybrid dynamics to reduce state uncertainty. We evaluate the proposed planner on a navigation task in the simulated domain and on an assembly task with a robotic manipulator, showing that our approach can solve tasks having high observation noise and nonlinear dynamics effectively with significantly lower computational costs compared to direct planning approaches.
Service robots that can assist humans in performing day-to-day tasks will need to be general-purp... more Service robots that can assist humans in performing day-to-day tasks will need to be general-purpose robots that can perform a wide array of tasks without much supervision from end-users. As they will be operating in unstructured and ever-changing human environments, they will need to be capable of adapting to their work environments quickly and learning to perform novel tasks within a few trials. However, current robots fall short of these requirements as they are generally highly specialized, can only perform fixed, predefined tasks reliably, and need to operate in controlled environments. One of the main reasons behind this big gap is that the current robots require complete and accurate information about their surroundings to function effectively, whereas, in human environments, robots will only have access to limited information about their tasks and environments. With incomplete information about its surroundings, a robot using pre-programmed or pre-learned motion policies wil...
We propose a method that efficiently learns distributions over articulation model parameters dire... more We propose a method that efficiently learns distributions over articulation model parameters directly from depth images without the need to know articulation model categories a priori. By contrast, existing methods that learn articulation models from raw observations typically only predict point estimates of the model parameters, which are insufficient to guarantee the safe manipulation of articulated objects. Our core contributions include a novel representation for distributions over rigid body transformations and articulation model parameters based on screw theory, von Mises-Fisher distributions, and Stiefel manifolds. Combining these concepts allows for an efficient, mathematically sound representation that implicitly satisfies the constraints that rigid body transformations and articulations must adhere to. Leveraging this representation, we introduce a novel deep learning based approach, DUST-net, that performs category-independent articulation model estimation while also prov...
Noisy observations coupled with nonlinear dynamics pose one of the biggest challenges in robot mo... more Noisy observations coupled with nonlinear dynamics pose one of the biggest challenges in robot motion planning. By decomposing the nonlinear dynamics into a discrete set of local dynamics models, hybrid dynamics provide a natural way to model nonlinear dynamics, especially in systems with sudden "jumps" in the dynamics, due to factors such as contacts. We propose a hierarchical POMDP planner that develops locally optimal motion plans for hybrid dynamics models. The hierarchical planner first develops a high-level motion plan to sequence the local dynamics models to be visited. The high-level plan is then converted into a detailed cost-optimized continuous state plan. This hierarchical planning approach results in a decomposition of the POMDP planning problem into smaller sub-parts that can be solved with significantly lower computational costs. The ability to sequence the visitation of local dynamics models also provides a powerful way to leverage the hybrid dynamics to re...
The difficulty of many robot controls tasks stems from stochasticity and partial observability co... more The difficulty of many robot controls tasks stems from stochasticity and partial observability coupled with highly nonlinear dynamics. We propose to approximate nonlinear system dynamics using hybrid dynamics models and extend the POMDP framework to hybrid systems. To do this, we introduce a Bayesian inference based hybrid state evolution model that can be used to develop feasible motion plans under partial observability.
2021 IEEE International Conference on Robotics and Automation (ICRA), 2021
Robots in human environments will need to interact with a wide variety of articulated objects suc... more Robots in human environments will need to interact with a wide variety of articulated objects such as cabinets, drawers, and dishwashers while assisting humans in performing day-today tasks. Existing methods either require objects to be textured or need to know the articulation model category a priori for estimating the model parameters for an articulated object. We propose ScrewNet, a novel approach that estimates an object's articulation model directly from depth images without requiring a priori knowledge of the articulation model category. ScrewNet uses screw theory to unify the representation of different articulation types and perform category-independent articulation model estimation. We evaluate our approach on two benchmarking datasets and three real-world objects and compare its performance with a current state-of-the-art method. Results demonstrate that ScrewNet can successfully estimate the articulation models and their parameters for novel objects across articulation model categories with better on average accuracy than the prior state-of-the-art method. Project page: https://pearl-utexas.github.io/ScrewNet/
Structural and Multidisciplinary Optimization, 2015
The field of robotics is evolving at a very high pace and with its increasing applicability in va... more The field of robotics is evolving at a very high pace and with its increasing applicability in varied fields, the need to incorporate optimization analysis in robot system design is becoming more prominent. The present work deals with the optimization of the design of a 7-link gripper. As actuators play a crucial role in functioning of the gripper, the actuation system (piezoelectric (PZ), in this case) is also taken into consideration while performing the optimization study. A minimalistic model of PZ actuator, consisting different series and parallel assembly arrangements for both mechanical and electrical parts of the PZ actuators, is proposed. To include the effects of connector spring, the relationship of force with actuator displacement is replaced by the relation between force and the displacement of point of actuation at the physical system. The design optimization problem of the gripper is a non-linear, multi modal optimization problem, which was originally formulated by Osyczka (2002). In the original work, however, the actuator was a 'constant output-force actuator model' providing a constant output without describing the internal structure. Thus, the actuator model was not integrated in the optimization study. Four different cases of the PZ modelling Bishakh Bhattacharya
Advances in Intelligent Systems and Computing, 2015
Piezoelectric (PZ) actuator is widely recognized for its high precision and displacement accuracy... more Piezoelectric (PZ) actuator is widely recognized for its high precision and displacement accuracy even at nanometer ranges. A minimalistic model is proposed in the present work, for PZ stack actuators. In the proposed model, various stack assembly arrangements have been assumed. Separate series and parallel assembly arrangements are suggested for both mechanical and electrical parts of the PZ actuators. The linearized constitutive equations formulated by IEEE, is considered to take into account the electromechanical coupling of the PZ actuator.
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
Sudden changes in the dynamics of robotic tasks, such as contact with an object or the latching o... more Sudden changes in the dynamics of robotic tasks, such as contact with an object or the latching of a door, are often viewed as inconvenient discontinuities that make manipulation difficult. However, when these transitions are wellunderstood, they can be leveraged to reduce uncertainty or aid manipulation-for example, wiggling a screw to determine if it is fully inserted or not. Current model-free reinforcement learning approaches require large amounts of data to learn to leverage such dynamics, scale poorly as problem complexity grows, and do not transfer well to significantly different problems. By contrast, hierarchical POMDP planning-based methods scale well via plan decomposition, work well on novel problems, and directly consider uncertainty, but often rely on precise hand-specified models and task decompositions. To combine the advantages of these opposing paradigms, we propose a new method, MICAH, which given unsegmented data of an object's motion under applied actions, (1) detects changepoints in the object motion model using action-conditional inference, (2) estimates the individual local motion models with their parameters, and (3) converts them into a hybrid automaton that is compatible with hierarchical POMDP planning. We show that model learning under MICAH is more accurate and robust to noise than prior approaches. Further, we combine MICAH with a hierarchical POMDP planner to demonstrate that the learned models are rich enough to be used for performing manipulation tasks under uncertainty that require the objects to be used in novel ways not encountered during training.
Piezoelectric (PZ) actuator is widely recognized for its high precision and displacement accuracy... more Piezoelectric (PZ) actuator is widely recognized for its high precision and displacement accuracy even at nanometer ranges. A minimalistic model is proposed in the present work, for PZ stack actuators. In the proposed model, various stack assembly arrangements have been assumed. Separate series and parallel assembly arrangements are suggested for both mechanical and electrical parts of the PZ actuators. The linearized constitutive equations formulated by IEEE, is considered to take into account the electromechanical coupling of the PZ actuator. In the proposed model, stiffness of the connectors in stack assembly have also been taken into account and is modeled as connector spring. To include the effects of connector spring, the relationships of force and voltage with actuator displacement is replaced by the relations between force and voltage with the displacement of point of actuation at the physical system. This leads to a more realistic model of PZ actuator to be used in applications requiring actuator to be modeled as a black-box. With the advent of technology, more and more complex and compact actuating system are emerging into existence. Engineering applications, such as in the field of robotics, that require a black-box modeling of actuators, need simplistic models of the actuators to decrease the computational complexity. The proposed model, being a minimalistic one, qualifies as an ideal candidate for such applications.
Noisy observations coupled with nonlinear dynamics pose one of the biggest challenges in robot mo... more Noisy observations coupled with nonlinear dynamics pose one of the biggest challenges in robot motion planning. By decomposing nonlinear dynamics into a discrete set of local dynamics models, hybrid dynamics provide a natural way to model nonlinear dynamics, especially in systems with sudden discontinuities in dynamics due to factors such as contacts. We propose a hierarchical POMDP planner that develops cost-optimized motion plans for hybrid dynamics models. The hierarchical planner first develops a high-level motion plan to sequence the local dynamics models to be visited and then converts it into a detailed continuous state plan. This hierarchical planning approach results in a decomposition of the POMDP planning problem into smaller sub-parts that can be solved with significantly lower computational costs. The ability to sequence the visitation of local dynamics models also provides a powerful way to leverage the hybrid dynamics to reduce state uncertainty. We evaluate the proposed planner on a navigation task in the simulated domain and on an assembly task with a robotic manipulator, showing that our approach can solve tasks having high observation noise and nonlinear dynamics effectively with significantly lower computational costs compared to direct planning approaches.
Service robots that can assist humans in performing day-to-day tasks will need to be general-purp... more Service robots that can assist humans in performing day-to-day tasks will need to be general-purpose robots that can perform a wide array of tasks without much supervision from end-users. As they will be operating in unstructured and ever-changing human environments, they will need to be capable of adapting to their work environments quickly and learning to perform novel tasks within a few trials. However, current robots fall short of these requirements as they are generally highly specialized, can only perform fixed, predefined tasks reliably, and need to operate in controlled environments. One of the main reasons behind this big gap is that the current robots require complete and accurate information about their surroundings to function effectively, whereas, in human environments, robots will only have access to limited information about their tasks and environments. With incomplete information about its surroundings, a robot using pre-programmed or pre-learned motion policies wil...
We propose a method that efficiently learns distributions over articulation model parameters dire... more We propose a method that efficiently learns distributions over articulation model parameters directly from depth images without the need to know articulation model categories a priori. By contrast, existing methods that learn articulation models from raw observations typically only predict point estimates of the model parameters, which are insufficient to guarantee the safe manipulation of articulated objects. Our core contributions include a novel representation for distributions over rigid body transformations and articulation model parameters based on screw theory, von Mises-Fisher distributions, and Stiefel manifolds. Combining these concepts allows for an efficient, mathematically sound representation that implicitly satisfies the constraints that rigid body transformations and articulations must adhere to. Leveraging this representation, we introduce a novel deep learning based approach, DUST-net, that performs category-independent articulation model estimation while also prov...
Noisy observations coupled with nonlinear dynamics pose one of the biggest challenges in robot mo... more Noisy observations coupled with nonlinear dynamics pose one of the biggest challenges in robot motion planning. By decomposing the nonlinear dynamics into a discrete set of local dynamics models, hybrid dynamics provide a natural way to model nonlinear dynamics, especially in systems with sudden "jumps" in the dynamics, due to factors such as contacts. We propose a hierarchical POMDP planner that develops locally optimal motion plans for hybrid dynamics models. The hierarchical planner first develops a high-level motion plan to sequence the local dynamics models to be visited. The high-level plan is then converted into a detailed cost-optimized continuous state plan. This hierarchical planning approach results in a decomposition of the POMDP planning problem into smaller sub-parts that can be solved with significantly lower computational costs. The ability to sequence the visitation of local dynamics models also provides a powerful way to leverage the hybrid dynamics to re...
The difficulty of many robot controls tasks stems from stochasticity and partial observability co... more The difficulty of many robot controls tasks stems from stochasticity and partial observability coupled with highly nonlinear dynamics. We propose to approximate nonlinear system dynamics using hybrid dynamics models and extend the POMDP framework to hybrid systems. To do this, we introduce a Bayesian inference based hybrid state evolution model that can be used to develop feasible motion plans under partial observability.
2021 IEEE International Conference on Robotics and Automation (ICRA), 2021
Robots in human environments will need to interact with a wide variety of articulated objects suc... more Robots in human environments will need to interact with a wide variety of articulated objects such as cabinets, drawers, and dishwashers while assisting humans in performing day-today tasks. Existing methods either require objects to be textured or need to know the articulation model category a priori for estimating the model parameters for an articulated object. We propose ScrewNet, a novel approach that estimates an object's articulation model directly from depth images without requiring a priori knowledge of the articulation model category. ScrewNet uses screw theory to unify the representation of different articulation types and perform category-independent articulation model estimation. We evaluate our approach on two benchmarking datasets and three real-world objects and compare its performance with a current state-of-the-art method. Results demonstrate that ScrewNet can successfully estimate the articulation models and their parameters for novel objects across articulation model categories with better on average accuracy than the prior state-of-the-art method. Project page: https://pearl-utexas.github.io/ScrewNet/
Structural and Multidisciplinary Optimization, 2015
The field of robotics is evolving at a very high pace and with its increasing applicability in va... more The field of robotics is evolving at a very high pace and with its increasing applicability in varied fields, the need to incorporate optimization analysis in robot system design is becoming more prominent. The present work deals with the optimization of the design of a 7-link gripper. As actuators play a crucial role in functioning of the gripper, the actuation system (piezoelectric (PZ), in this case) is also taken into consideration while performing the optimization study. A minimalistic model of PZ actuator, consisting different series and parallel assembly arrangements for both mechanical and electrical parts of the PZ actuators, is proposed. To include the effects of connector spring, the relationship of force with actuator displacement is replaced by the relation between force and the displacement of point of actuation at the physical system. The design optimization problem of the gripper is a non-linear, multi modal optimization problem, which was originally formulated by Osyczka (2002). In the original work, however, the actuator was a 'constant output-force actuator model' providing a constant output without describing the internal structure. Thus, the actuator model was not integrated in the optimization study. Four different cases of the PZ modelling Bishakh Bhattacharya
Advances in Intelligent Systems and Computing, 2015
Piezoelectric (PZ) actuator is widely recognized for its high precision and displacement accuracy... more Piezoelectric (PZ) actuator is widely recognized for its high precision and displacement accuracy even at nanometer ranges. A minimalistic model is proposed in the present work, for PZ stack actuators. In the proposed model, various stack assembly arrangements have been assumed. Separate series and parallel assembly arrangements are suggested for both mechanical and electrical parts of the PZ actuators. The linearized constitutive equations formulated by IEEE, is considered to take into account the electromechanical coupling of the PZ actuator.
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
Sudden changes in the dynamics of robotic tasks, such as contact with an object or the latching o... more Sudden changes in the dynamics of robotic tasks, such as contact with an object or the latching of a door, are often viewed as inconvenient discontinuities that make manipulation difficult. However, when these transitions are wellunderstood, they can be leveraged to reduce uncertainty or aid manipulation-for example, wiggling a screw to determine if it is fully inserted or not. Current model-free reinforcement learning approaches require large amounts of data to learn to leverage such dynamics, scale poorly as problem complexity grows, and do not transfer well to significantly different problems. By contrast, hierarchical POMDP planning-based methods scale well via plan decomposition, work well on novel problems, and directly consider uncertainty, but often rely on precise hand-specified models and task decompositions. To combine the advantages of these opposing paradigms, we propose a new method, MICAH, which given unsegmented data of an object's motion under applied actions, (1) detects changepoints in the object motion model using action-conditional inference, (2) estimates the individual local motion models with their parameters, and (3) converts them into a hybrid automaton that is compatible with hierarchical POMDP planning. We show that model learning under MICAH is more accurate and robust to noise than prior approaches. Further, we combine MICAH with a hierarchical POMDP planner to demonstrate that the learned models are rich enough to be used for performing manipulation tasks under uncertainty that require the objects to be used in novel ways not encountered during training.
Piezoelectric (PZ) actuator is widely recognized for its high precision and displacement accuracy... more Piezoelectric (PZ) actuator is widely recognized for its high precision and displacement accuracy even at nanometer ranges. A minimalistic model is proposed in the present work, for PZ stack actuators. In the proposed model, various stack assembly arrangements have been assumed. Separate series and parallel assembly arrangements are suggested for both mechanical and electrical parts of the PZ actuators. The linearized constitutive equations formulated by IEEE, is considered to take into account the electromechanical coupling of the PZ actuator. In the proposed model, stiffness of the connectors in stack assembly have also been taken into account and is modeled as connector spring. To include the effects of connector spring, the relationships of force and voltage with actuator displacement is replaced by the relations between force and voltage with the displacement of point of actuation at the physical system. This leads to a more realistic model of PZ actuator to be used in applications requiring actuator to be modeled as a black-box. With the advent of technology, more and more complex and compact actuating system are emerging into existence. Engineering applications, such as in the field of robotics, that require a black-box modeling of actuators, need simplistic models of the actuators to decrease the computational complexity. The proposed model, being a minimalistic one, qualifies as an ideal candidate for such applications.
Uploads
Papers by Ajinkya Jain