Abstract: An autonomous mobile robot (AMR) with a single modular platform to mount plurality of material handling units is provided. The AMR includes a monolithic chassis; a top plate includes plurality of standoffs to mount at least one material handling units; the plurality of standoffs are integrated on top of the top plate; drive wheels are coupled to a wheel mount as a single unit to form a drive wheel assembly; a suspension unit is coupled symmetrically in between two main bodies which corresponds to the monolithic chassis and the drive wheel assembly with spring enclosures, suspension shafts, and coil springs; a set of side plates connect the monolithic chassis on the AMR. The top plate is sandwiched between the plurality of standoffs and the monolithic chassis. A load is transferred from the plurality of material handling units through the plurality of standoffs and the top plate to the monolithic chassis.

Abstract: Object manipulation in warehouses and logistics facilities is a challenging task because of the unstructured environment. The unstructured environment can have items/objects with different form factors, weight, shape, and size. Traditionally, multiple robots have been used to handle for specific task to be performed by an individual robot which requires high floor. This leads to higher cost and infrastructure. Embodiments of the present disclosure provide a gripper apparatus that addresses a single gripper design handling multiple parcels, wherein the apparatus consists of ‘m’ fingers parallel to each other and can be independently controlled through actuators, each finger has a force sensors feedback and also actuators which are controlled with force. Each finger comprises a linear slider for actuation for gripping objects and wherein bottom fingers are moved to provide enough gravity support.

Abstract: Conventionally, loading and unloading pallets occurred in a factory like environment, wherein traditional systems were used for stacking pallets vertically for retrieval thereof. However, these pallets arrive from a roller conveyer and such set-ups are purely based on the concept of storage purpose and lack in palletizing and depalletizing in effective manner. Embodiments of the present disclosure provide pallet loading and unloading apparatus for automated objects manipulation, wherein pallet(s) from a forklift jack arrives on a linear slider assembly for movement of pallet from loading area to manipulating area using two double-sided cylinders associated thereof. Rollers comprised in apparatus provide flexibility to linear slider to slide freely on top. Manipulator performs palletizing and depalletizing as applicable.

Abstract: An autonomous mobile robot (AMR) with a single modular platform to mount plurality of material handling units is provided. The AMR includes a monolithic chassis; a top plate includes plurality of standoffs to mount at least one material handling units; the plurality of standoffs are integrated on top of the top plate; drive wheels are coupled to a wheel mount as a single unit to form a drive wheel assembly; a suspension unit is coupled symmetrically in between two main bodies which corresponds to the monolithic chassis and the drive wheel assembly with spring enclosures, suspension shafts, and coil springs; a set of side plates connect the monolithic chassis on the AMR. The top plate is sandwiched between the plurality of standoffs and the monolithic chassis. A load is transferred from the plurality of material handling units through the plurality of standoffs and the top plate to the monolithic chassis.

Abstract: Conventionally, loading and unloading pallets occurred in a factory like environment, wherein traditional systems were used for stacking pallets vertically for retrieval thereof. However, these pallets arrive from a roller conveyer and such set-ups are purely based on the concept of storage purpose and lack in palletizing and depalletizing in effective manner. Embodiments of the present disclosure provide pallet loading and unloading apparatus for automated objects manipulation, wherein pallet(s) from a forklift jack arrives on a linear slider assembly for movement of pallet from loading area to manipulating area using two double-sided cylinders associated thereof. Rollers comprised in apparatus provide flexibility to linear slider to slide freely on top. Manipulator performs palletizing and depalletizing as applicable.

Abstract: Object manipulation in warehouses and logistics facilities is a challenging task because of the unstructured environment. The unstructured environment can have items/objects with different form factors, weight, shape, and size. Traditionally, multiple robots have been used to handle for specific task to be performed by an individual robot which requires high floor. This leads to higher cost and infrastructure. Embodiments of the present disclosure provide a gripper apparatus that addresses a single gripper design handling multiple parcels, wherein the apparatus consists of cm? fingers parallel to each other and can be independently controlled through actuators, each finger has a force sensors feedback and also actuators which are controlled with force. Each finger comprises a linear slider for actuation for gripping objects and wherein bottom fingers are moved to provide enough gravity support.

Abstract: Object annotation is images is tedious time consuming task when large volume of data needs to annotated. Existing methods limit to semiautomatic approaches for annotation. The embodiments herein provide a method and system for a deep network based architecture for automatic object annotation. The deep network utilized is a two stage network with first stage as an annotation model comprising a Faster Region-based Fully Convolutional Networks (F-RCNN) and Region-based Fully Convolutional Networks (RFCN) providing for two class classification to generate annotated images from a set of single object test images. Further, the newly annotated test object images are then used to synthetically generate cluttered images and their corresponding annotations, which are used to train the second stage of the deep network comprising the multi-class object detection/classification model designed using the F-RCNN and the RFCN as base networks to automatically annotate input test image in real time.

Abstract: This disclosure relates generally to an apparatus for loading and unloading of unit loads in freight. A mobile base platform of the apparatus includes a telescopic railing and a telescopic conveyor, wherein the telescopic conveyor is mounted on top of the telescopic railing and the tail end of the telescopic railing is mounted on the front end of mobile base platform. A mechanical connector is adapted to connect the front end of a telescopic conveyor with the front end of the telescopic railing, wherein the mechanical connector enables the telescopic robotic mounting plate coupled to the telescopic railing to move in relation to the telescopic conveyor. The telescopic conveyor and the telescopic railing is moved towards the forward position inside the carrying body, where the forward position movement is enabled by the mechanical link to unload freight.

Abstract: Object annotation is images is tedious time consuming task when large volume of data needs to annotated. Existing methods limit to semiautomatic approaches for annotation. The embodiments herein provide a method and system for a deep network based architecture for automatic object annotation. The deep network utilized is a two stage network with first stage as an annotation model comprising a Faster Region-based Fully Convolutional Networks (F-RCNN) and Region-based Fully Convolutional Networks (RFCN) providing for two class classification to generate annotated images from a set of single object test images. Further, the newly annotated test object images are then used to synthetically generate cluttered images and their corresponding annotations, which are used to train the second stage of the deep network comprising the multi-class object detection/classification model designed using the F-RCNN and the RFCN as base networks to automatically annotate input test image in real time.

Abstract: Systems and methods for detecting grasping poses for handling target objects is disclosed. The system solves problem of grasp pose detection and finding suitable graspable affordance for picking objects from a confined and cluttered space, such as the bins of a rack in a retail warehouse by creating multiple surface segments within bounding box obtained from a neural network based object recognition module. Surface patches are created using a region growing technique in depth space based on surface normals directions. A Gaussian Mixture Model based on color and depth curvature is used to segment surfaces belonging to target object from background, thereby overcoming inaccuracy of object recognition module trained on a smaller dataset resulting in larger bounding boxes for target objects. Target object shape is identified by using empirical rules on surface attributes thereby detecting graspable affordances and poses thus avoiding collision with neighboring objects and grasping objects more successfully.

Abstract: This disclosure relates generally to an apparatus for loading and unloading of unit loads in freight. A mobile base platform of the apparatus includes a telescopic railing and a telescopic conveyor, wherein the telescopic conveyor is mounted on top of the telescopic railing and the tail end of the telescopic railing is mounted on the front end of mobile base platform. A mechanical connector is adapted to connect the front end of a telescopic conveyor with the front end of the telescopic railing, wherein the mechanical connector enables the telescopic robotic mounting plate coupled to the telescopic railing to move in relation to the telescopic conveyor. The telescopic conveyor and the telescopic railing is moved towards the forward position inside the carrying body, where the forward position movement is enabled by the mechanical link to unload freight.

Abstract: The system and method for recognizing and counting products within images is disclosed. The products are recognized by carrying out a nearest-neighbor search in the template feature space using a k-d tree and the product count is then obtained by using a maximum feature repeatability index for each identified feature. The system also obtains product arrangement by fitting bounding boxes around each identified product. The count of boxes thus obtained may also provide the exact number of discrete products visible in an image. A second stage of grid-based search is also carried out in the neighborhood of each detected product to detect new products that might have been missed out in the previous step. This detection is based on a confidence measure including information like histogram matching and spatial location of products. This system is also useful in verifying planogram compliance for a given product.

Abstract: A gripper device and method is provided. The method includes capturing, using an electronic device, information of an object that is indicative of holding position; determining, using the information, by a hardware processor, an optimal holding orientation and an optimal movement of at least one of (i) a plurality of fingers, or (ii) a plurality of suction cups of a gripper device; identifying the at least one of (i) the plurality of fingers, and (ii) the plurality of suction cups as one or more grasping components based on the information, the optimal holding orientation and the optimal movement; and enabling, using an actuator, the one or more identified grasping components to grasp the object based on the information, the optimal holding orientation and the optimal movement.

Abstract: Systems and methods for detecting grasping poses for handling target objects is disclosed. The system solves problem of grasp pose detection and finding suitable graspable affordance for picking objects from a confined and cluttered space, such as the bins of a rack in a retail warehouse by creating multiple surface segments within bounding box obtained from a neural network based object recognition module. Surface patches are created using a region growing technique in depth space based on surface normals directions. A Gaussian Mixture Model based on color and depth curvature is used to segment surfaces belonging to target object from background, thereby overcoming inaccuracy of object recognition module trained on a smaller dataset resulting in larger bounding boxes for target objects. Target object shape is identified by using empirical rules on surface attributes thereby detecting graspable affordances and poses thus avoiding collision with neighboring objects and grasping objects more successfully.

Abstract: A gripper device and method is provided. The method includes capturing, using an electronic device, information of an object that is indicative of holding position; determining, using the information, by a hardware processor, an optimal holding orientation and an optimal movement of at least one of (i) a plurality of fingers, or (ii) a plurality of suction cups of a gripper device; identifying the at least one of (i) the plurality of fingers, and (ii) the plurality of suction cups as one or more grasping components based on the information, the optimal holding orientation and the optimal movement; and enabling, using an actuator, the one or more identified grasping components to grasp the object based on the information, the optimal holding orientation and the optimal movement.